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

    Neuronpedia

    INDEX
    Explanations

    timestamps mentioned in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    sequences relating to numerical data and time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quez
    -0.75
    fruit
    -0.73
    interstitial
    -0.72
    jected
    -0.68
    rely
    -0.67
    obal
    -0.66
    unal
    -0.66
    ographically
    -0.65
    otto
    -0.65
    alez
    -0.64
    POSITIVE LOGITS
    mAh
    0.83
    ISTER
    0.78
    nm
    0.77
     GHz
    0.73
    gp
    0.73
     hrs
    0.72
    rpm
    0.72
     UTC
    0.69
     NOTICE
    0.69
    aneous
    0.68
    Act Density 0.028%

    No Known Activations