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

    Neuronpedia

    INDEX
    Explanations

    currency values

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gaze
    -0.85
     wildlife
    -0.79
     haunted
    -0.78
     habit
    -0.77
     lull
    -0.75
     resur
    -0.74
     beck
    -0.73
     ne
    -0.73
     ent
    -0.73
     fle
    -0.72
    POSITIVE LOGITS
    excluding
    1.70
    depending
    1.61
    approximately
    1.55
    average
    1.50
    including
    1.46
    rounded
    1.43
    total
    1.42
    according
    1.41
    minimum
    1.38
    equal
    1.35
    Act Density 0.080%

    No Known Activations