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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or refusals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.60
    帖最后由
    -0.59
    lagte
    -0.53
     actually
    -0.51
     الوطنيه
    -0.50
    addGap
    -0.49
    kloped
    -0.48
    STRICT
    -0.48
    <?
    -0.47
    CloseOperation
    -0.47
    POSITIVE LOGITS
     countenance
    0.70
     tolerated
    0.66
    Rüyada
    0.65
     tolerate
    0.61
     lightly
    0.61
    üyada
    0.57
    꿈
    0.57
    hoeddwyd
    0.56
    toler
    0.56
    ANTLR
    0.55
    Act Density 0.342%

    No Known Activations