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

    Neuronpedia

    INDEX
    Explanations

    data on financial amounts and transactions

    oai_token-act-pair · gpt-3.5-turbo

    the word "in" indicating the presence of location or context within various sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PIN
    -0.72
    few
    -0.72
    mentioned
    -0.72
    deck
    -0.69
    HAEL
    -0.68
    rily
    -0.68
    station
    -0.67
    ¤
    -0.67
    rett
    -0.67
    bryce
    -0.66
    POSITIVE LOGITS
     increments
    0.96
     total
    0.95
     advance
    0.92
    effic
    0.89
     aggregate
    0.88
     excess
    0.88
     USD
    0.86
    ordinate
    0.85
    efficiency
    0.84
     unison
    0.84
    Act Density 0.098%

    No Known Activations