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

    Neuronpedia

    INDEX
    Explanations

    significant numbers or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atown
    -0.69
    atus
    -0.69
     redeemed
    -0.67
     renewed
    -0.65
    rists
    -0.64
     benefic
    -0.63
     cous
    -0.62
    rived
    -0.62
     elig
    -0.60
     Caption
    -0.60
    POSITIVE LOGITS
    20439
    0.85
    pointer
    0.76
    %-
    0.75
    ãĥĩãĤ£
    0.73
    dB
    0.73
     months
    0.72
    %"
    0.71
    ench
    0.70
    RF
    0.68
    ½
    0.67
    Act Density 0.101%

    No Known Activations