Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    medical and political terms, societal issues, and government-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to political and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.81
    pex
    -0.70
     himself
    -0.70
     herself
    -0.64
     Canaver
    -0.64
    imming
    -0.63
    ãĥĥãĤ¯
    -0.61
    nikov
    -0.60
    ãĤ°
    -0.60
    Attributes
    -0.59
    POSITIVE LOGITS
     selves
    1.07
     ourselves
    0.79
     ancestors
    0.77
     asses
    0.75
     endeavors
    0.75
    INESS
    0.72
     counterparts
    0.70
     brethren
    0.68
     cousins
    0.67
     motto
    0.66
    Act Density 0.258%

    No Known Activations