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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to potential gains or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.66
     Sloan
    -0.63
    sbm
    -0.60
    Revolution
    -0.59
    maxwell
    -0.58
     sqor
    -0.56
     Disability
    -0.55
     Died
    -0.55
     Bronze
    -0.55
     plans
    -0.55
    POSITIVE LOGITS
    uate
    0.77
    èĢħ
    0.70
    ezvous
    0.70
    idious
    0.69
    tails
    0.68
    alogue
    0.67
    enance
    0.67
    ogue
    0.66
    ÙĴ
    0.62
    luence
    0.62
    Act Density 0.265%

    No Known Activations