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

    Neuronpedia

    INDEX
    Explanations

    actions or stances taken by individuals related to ethical or controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to ethical choices and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bellev
    -0.66
    amina
    -0.64
    waters
    -0.63
     Ramos
    -0.61
     Ambrose
    -0.60
    isters
    -0.59
    resa
    -0.59
    verbs
    -0.57
    enthal
    -0.56
     throb
    -0.56
    POSITIVE LOGITS
    depending
    1.17
     depending
    1.17
     thereof
    1.06
     alike
    0.90
     versa
    0.87
    SPONSORED
    0.82
     whichever
    0.81
    atever
    0.80
     anywhere
    0.79
     respectively
    0.78
    Act Density 0.320%

    No Known Activations