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

    Neuronpedia

    INDEX
    Explanations

    texts indicating Python exceptions being thrown

    oai_token-act-pair · gpt-3.5-turbo

    instances of high-scoring plays or performances in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occas
    -0.80
     endeav
    -0.78
     proport
    -0.78
     tremend
    -0.77
     disillusion
    -0.70
     exha
    -0.69
     imperson
    -0.69
     footing
    -0.69
     underest
    -0.68
     experien
    -0.67
    POSITIVE LOGITS
    Posted
    1.51
    posted
    1.26
    ³³³³³³³³³³³³³³³³
    1.10
    ³³³³³³³³
    1.04
    Article
    1.03
    ³³³³
    1.02
    Anyway
    1.02
    UPDATE
    0.99
    Update
    0.99
    Anonymous
    0.97
    Act Density 0.519%

    No Known Activations