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

    Neuronpedia

    INDEX
    Explanations

    percentage values

    oai_token-act-pair · gpt-3.5-turbo

    instances of percentages and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.77
    worldly
    -0.74
    rants
    -0.72
    laden
    -0.71
     rom
    -0.71
    kefeller
    -0.69
    ollah
    -0.66
     Rav
    -0.66
    zie
    -0.65
    emies
    -0.64
    POSITIVE LOGITS
    +)
    0.76
    +.
    0.69
     percentile
    0.69
     utilization
    0.67
    imet
    0.66
     reuse
    0.65
     accuracy
    0.65
    +,
    0.65
     probability
    0.64
    PsyNetMessage
    0.64
    Act Density 0.056%

    No Known Activations