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

    Neuronpedia

    INDEX
    Explanations

    contractions indicating negation or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.66
     صوتيه
    -0.53
    ,]
    -0.52
    )$/,
    -0.48
    клопе
    -0.48
    $/,
    -0.48
     समीक्षक
    -0.46
     treo
    -0.46
    )}+
    -0.45
    vale
    -0.45
    POSITIVE LOGITS
    ´
    0.96
    \'
    0.84
     myſelf
    0.81
     HasFactory
    0.79
    apos
    0.73
    berdayakan
    0.73
    ͛
    0.72
     uovo
    0.70
     étoit
    0.68
    tvguidetime
    0.68
    Act Density 0.287%

    No Known Activations