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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals who are highly skilled or knowledgeable in a particular area

    oai_token-act-pair · gpt-3.5-turbo

    references to mastery or experts in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.97
    soType
    -0.78
    thens
    -0.70
     Ey
    -0.69
    heter
    -0.69
    cially
    -0.69
     protestors
    -0.69
     Holl
    -0.69
     Discrimination
    -0.68
    idth
    -0.67
    POSITIVE LOGITS
     master
    3.81
     masters
    2.93
     Master
    2.46
    master
    2.30
    Master
    2.24
    masters
    1.85
     mastering
    1.69
     Masters
    1.68
     mastered
    1.53
     mistress
    1.52
    Act Density 0.022%

    No Known Activations