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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant entities and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akable
    -0.80
    zy
    -0.67
     Saiyan
    -0.65
    thora
    -0.63
    zees
    -0.63
    xit
    -0.62
    constitutional
    -0.61
    lay
    -0.60
     Bale
    -0.59
    ä
    -0.59
    POSITIVE LOGITS
     itself
    0.73
     responded
    0.70
    goers
    0.69
     inspector
    0.66
     brass
    0.65
     Inspector
    0.64
     staffer
    0.64
     retaliate
    0.63
     insiders
    0.63
     premises
    0.62
    Act Density 0.816%

    No Known Activations