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

    percentage values and their associated metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icon
    -0.70
    zie
    -0.68
     Rav
    -0.67
    worldly
    -0.67
    ipples
    -0.66
    kefeller
    -0.65
    ĪĴ
    -0.63
    pload
    -0.63
    emed
    -0.62
    achus
    -0.61
    POSITIVE LOGITS
     utilization
    0.87
     humidity
    0.82
    PsyNetMessage
    0.79
     accuracy
    0.78
     occupancy
    0.77
     confidence
    0.70
     ABV
    0.69
     reuse
    0.67
     completion
    0.67
     reservation
    0.67
    Act Density 0.065%

    No Known Activations