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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names with the prefix "Pe"

    oai_token-act-pair · gpt-3.5-turbo

    words that contain consonant clusters or prefixes/suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLA
    -0.67
     Bauer
    -0.64
     Sabha
    -0.64
    Hig
    -0.63
     LF
    -0.60
     Quentin
    -0.58
    }}}
    -0.58
     Mara
    -0.57
     tert
    -0.56
     Wer
    -0.56
    POSITIVE LOGITS
    aneers
    0.88
    eworthy
    0.82
    ongyang
    0.82
    seed
    0.82
    ciation
    0.82
    ancy
    0.82
    iddy
    0.79
    inator
    0.78
    ophobic
    0.77
    ishly
    0.75
    Act Density 0.080%

    No Known Activations