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

    Neuronpedia

    INDEX
    Explanations

    specific times mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers or time-related data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.78
    unal
    -0.76
     disproportion
    -0.73
    leans
    -0.73
    assic
    -0.71
    warts
    -0.70
    loo
    -0.70
    omnia
    -0.70
    jected
    -0.68
     strugg
    -0.67
    POSITIVE LOGITS
    mAh
    0.97
     NOTICE
    0.86
     UTC
    0.84
    ISTER
    0.84
    enced
    0.82
    nm
    0.80
     GMT
    0.80
    0100
    0.79
    UTC
    0.76
     hrs
    0.76
    Act Density 0.022%

    No Known Activations