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

    Neuronpedia

    INDEX
    Explanations

    metrics related to percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    談社
    -0.85
    jasama
    -0.85
    ("'"
    -0.84
     paille
    -0.81
    ingtones
    -0.79
    waffe
    -0.79
     roulant
    -0.78
     gezet
    -0.78
     chaude
    -0.78
    AutoScaleMode
    -0.78
    POSITIVE LOGITS
     percent
    1.31
     Prozent
    1.03
    percent
    0.96
     Percent
    0.86
     PERCENT
    0.86
    Percent
    0.81
     ciento
    0.79
     persen
    0.75
     cent
    0.75
     процентов
    0.74
    Act Density 0.057%

    No Known Activations