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

    Neuronpedia

    INDEX
    Explanations

    unexpected occurrences or events

    oai_token-act-pair · gpt-3.5-turbo

    references to occurrences or situations that are surprising or unanticipated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nan
    -0.94
    burgh
    -0.84
    ogun
    -0.83
    tein
    -0.82
    claimer
    -0.82
    rio
    -0.80
    xia
    -0.80
    builders
    -0.80
    ©¶æ
    -0.77
    bourg
    -0.77
    POSITIVE LOGITS
     unexpected
    1.03
     surprises
    0.88
    aneously
    0.87
    LY
    0.84
    cffffcc
    0.83
     twists
    0.80
     occurrences
    0.78
     circumstances
    0.77
     pregnancies
    0.74
     revelations
    0.74
    Act Density 0.025%

    No Known Activations