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

    Neuronpedia

    INDEX
    Explanations

    words related to exaggeration or intensity

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with conditions of excess or extreme states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emouth
    -0.70
    baum
    -0.68
     ABE
    -0.67
    iage
    -0.65
    çĦ
    -0.63
    SPONSORED
    -0.61
    wick
    -0.61
     Grounds
    -0.60
     Folder
    -0.60
    ulhu
    -0.59
    POSITIVE LOGITS
    ulic
    0.90
    emic
    0.84
    uating
    0.80
    opter
    0.80
    catentry
    0.77
    ilic
    0.76
    ersive
    0.73
    inem
    0.73
    nir
    0.71
    etch
    0.68
    Act Density 0.111%

    No Known Activations