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

    Neuronpedia

    INDEX
    Explanations

    numbers associated with the 18th item in a list or sequence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number "18" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orter
    -0.74
    achu
    -0.68
    ical
    -0.67
    ointed
    -0.67
    atown
    -0.65
    orc
    -0.64
    olicy
    -0.64
    othe
    -0.63
    enhagen
    -0.62
    endish
    -0.62
    POSITIVE LOGITS
    650
    1.20
    02
    1.04
    05
    1.02
    03
    1.02
    09
    0.99
    06
    0.99
    58
    0.97
    94
    0.97
    91
    0.94
    04
    0.94
    Act Density 0.043%

    No Known Activations