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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to various individuals and entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Burg
    -0.63
    Tes
    -0.60
    cientious
    -0.58
     lett
    -0.58
     chronological
    -0.58
     understatement
    -0.56
    piring
    -0.55
     NRL
    -0.55
     Corpus
    -0.55
     adolesc
    -0.53
    POSITIVE LOGITS
     specializes
    0.84
     reportedly
    0.82
     testified
    0.78
     died
    0.77
     apologized
    0.77
    rite
    0.76
     consisted
    0.76
    's
    0.74
    enegger
    0.73
     was
    0.73
    Act Density 0.422%

    No Known Activations