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

    Neuronpedia

    INDEX
    Explanations

    numbers, particularly relating to quantity

    oai_token-act-pair · gpt-3.5-turbo

    references to large numerical quantities or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    krit
    -0.71
    ufact
    -0.70
    venge
    -0.69
    estine
    -0.68
    ifice
    -0.67
     tremend
    -0.67
    alys
    -0.66
    ocol
    -0.65
    pport
    -0.65
    ienne
    -0.63
    POSITIVE LOGITS
    +
    1.19
    mAh
    0.99
    lbs
    0.97
     lbs
    0.96
    lb
    0.96
    +.
    0.94
     miles
    0.93
     volts
    0.93
    km
    0.93
    rpm
    0.92
    Act Density 0.078%

    No Known Activations