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

    phrases related to numerical statistics and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.75
    kefeller
    -0.72
    worldly
    -0.72
    icon
    -0.71
     Rav
    -0.65
    rants
    -0.64
    rir
    -0.63
    ollah
    -0.62
     dign
    -0.62
    ãĥ¤
    -0.61
    POSITIVE LOGITS
    +)
    0.73
    PsyNetMessage
    0.71
     percentile
    0.70
     utilization
    0.69
     humidity
    0.68
    +.
    0.67
     percent
    0.66
     reuse
    0.66
    imet
    0.65
     disapprove
    0.64
    Act Density 0.064%

    No Known Activations