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

    Neuronpedia

    INDEX
    Explanations

    phrases describing someone's most well-known role or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate someone's notable achievements or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plan
    -0.72
    uly
    -0.65
    xit
    -0.65
    aminer
    -0.64
    otom
    -0.64
    bern
    -0.63
    docs
    -0.63
     train
    -0.63
    onest
    -0.63
    reen
    -0.63
    POSITIVE LOGITS
     Sprite
    0.76
     landmarks
    0.65
     Occupations
    0.64
    Offline
    0.64
     thous
    0.63
     Chap
    0.63
     fame
    0.62
     Hud
    0.62
    entious
    0.62
     Scene
    0.61
    Act Density 0.040%

    No Known Activations