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

    Neuronpedia

    INDEX
    Explanations

    financial estimates or numbers

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to estimated quantities or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GU
    -0.89
    uits
    -0.83
    neys
    -0.77
    eyes
    -0.66
    tested
    -0.66
    jri
    -0.64
    hots
    -0.63
    reditary
    -0.63
    AMA
    -0.63
    woods
    -0.62
    POSITIVE LOGITS
     âĸĪ
    0.85
     amount
    0.83
     3000
    0.79
     5000
    0.77
     350
    0.77
     400
    0.76
     300
    0.76
     250
    0.75
     sixty
    0.75
     thirty
    0.75
    Act Density 0.030%

    No Known Activations