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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibility or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athing
    -0.76
    âĵĺ
    -0.73
    lier
    -0.68
    let
    -0.67
    icial
    -0.66
    ATS
    -0.66
    ICO
    -0.63
    LET
    -0.61
    managed
    -0.61
    lets
    -0.61
    POSITIVE LOGITS
     seem
    1.34
     sound
    1.12
     imply
    1.00
     sounds
    0.99
     disappoint
    0.95
     appear
    0.94
     be
    0.94
     horr
    0.93
     offend
    0.93
     blush
    0.92
    Act Density 0.093%

    No Known Activations