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

    Neuronpedia

    INDEX
    Explanations

    words related to professional accomplishments and qualities

    oai_token-act-pair · gpt-3.5-turbo

    evaluations and opinions about individuals' abilities or performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %%
    -0.59
    Detailed
    -0.56
    arest
    -0.54
    ocaly
    -0.54
    Ó
    -0.53
    pmwiki
    -0.52
     SECTION
    -0.52
    âĢ
    -0.52
    FAQ
    -0.52
    FTWARE
    -0.51
    POSITIVE LOGITS
     he
    1.74
     his
    1.65
     him
    1.46
    his
    1.40
    His
    1.30
    He
    1.28
     He
    1.18
     himself
    1.10
     His
    1.08
    he
    1.06
    Act Density 1.292%

    No Known Activations