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

    Neuronpedia

    INDEX
    Explanations

    proper nouns indicating entities in a global context

    oai_token-act-pair · gpt-3.5-turbo

    references to global status or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.96
    veyard
    -0.91
    edin
    -0.76
    ients
    -0.76
    MENTS
    -0.71
    shapeshifter
    -0.70
     COUNTY
    -0.70
    maid
    -0.69
    EStream
    -0.69
    iple
    -0.68
    POSITIVE LOGITS
    wide
    0.95
     renown
    0.88
     premiere
    0.87
     renowned
    0.85
     heavyweight
    0.84
     wide
    0.81
     champion
    0.80
     championship
    0.77
     warming
    0.76
     domination
    0.74
    Act Density 0.052%

    No Known Activations