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

    Neuronpedia

    INDEX
    Explanations

    phrases related to creating or configuring software tools and functionalities

    oai_token-act-pair · gpt-3.5-turbo

    instructions or commands related to creating something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bey
    -0.76
    phia
    -0.73
     preached
    -0.70
    EGA
    -0.68
    pha
    -0.64
    atti
    -0.63
    osate
    -0.62
    ishops
    -0.62
    iere
    -0.62
    ĸļ
    -0.60
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    0.83
    Instance
    0.81
    ividual
    0.74
    idable
    0.74
    urable
    0.72
     batch
    0.70
    slave
    0.68
    ezvous
    0.68
     anew
    0.68
     batches
    0.67
    Act Density 0.038%

    No Known Activations