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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names related to individuals and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    posted
    -0.82
    DN
    -0.80
    æ©
    -0.70
     taxp
    -0.64
    verbs
    -0.63
    vez
    -0.62
    ources
    -0.61
     hindsight
    -0.61
    quest
    -0.60
    :{
    -0.60
    POSITIVE LOGITS
    uku
    0.86
    inki
    0.77
    hof
    0.70
    atu
    0.69
    adesh
    0.67
    zees
    0.66
    atta
    0.66
    vu
    0.65
    urst
    0.65
    zee
    0.65
    Act Density 0.296%

    No Known Activations