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

    Neuronpedia

    INDEX
    Explanations

    references to percentages and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    談社
    -0.97
     Roskov
    -0.89
    <()>
    -0.81
    TintMode
    -0.79
    !*\
    -0.76
    lewati
    -0.75
    rawQuery
    -0.74
     Orrell
    -0.74
    paravant
    -0.74
     Bevan
    -0.74
    POSITIVE LOGITS
     cent
    0.99
     cents
    0.96
     percent
    0.89
     Prozent
    0.84
    Cent
    0.84
    cent
    0.81
     Chaudh
    0.81
     PERCENT
    0.78
     Cents
    0.78
     Cent
    0.77
    Act Density 0.112%

    No Known Activations