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

    Neuronpedia

    INDEX
    Explanations

    words related to responsibility and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @nate
    -0.15
    OffsetTable
    -0.15
    acons
    -0.14
    लत
    -0.14
    #
    -0.14
     Dul
    -0.14
    aye
    -0.14
    iв
    -0.14
    /DTD
    -0.14
    érica
    -0.14
    POSITIVE LOGITS
    ard
    0.86
    ards
    0.73
    ARD
    0.62
    аÑĢд
    0.59
     ard
    0.56
    arding
    0.54
    arded
    0.53
    arda
    0.51
    ارد
    0.51
    ARDS
    0.50
    Act Density 0.078%

    No Known Activations