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

    Neuronpedia

    INDEX
    Explanations

    excerpts containing beliefs or thoughts by individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of belief or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kn
    -0.62
    Holy
    -0.59
    see
    -0.59
    clock
    -0.57
    ble
    -0.57
    ãģĹ
    -0.56
    cl
    -0.55
    begin
    -0.55
    mentioned
    -0.54
    scroll
    -0.53
    POSITIVE LOGITS
    olate
    0.86
    paces
    0.78
    aspers
    0.77
    creen
    0.75
    olated
    0.75
    omething
    0.71
    iewicz
    0.71
    ighed
    0.70
    hement
    0.68
    hirt
    0.65
    Act Density 0.194%

    No Known Activations