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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations or specific organizations, potentially news articles or blog posts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    oche
    -1.12
    osaurus
    -0.99
     suspic
    -0.96
     strokes
    -0.95
     oun
    -0.93
     plur
    -0.93
     outl
    -0.93
     wielded
    -0.92
    sson
    -0.92
     symp
    -0.90
    POSITIVE LOGITS
    BUT
    1.29
     âĢİ
    1.26
    reads
    1.15
    etc
    1.13
    eat
    1.09
    uh
    1.07
    sort
    1.06
    eas
    1.06
    girls
    1.06
    SIGN
    1.05
    Act Density 0.607%

    No Known Activations