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

    Neuronpedia

    INDEX
    Explanations

    negations or statements of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >{@
    -0.74
    AutoScaleMode
    -0.62
    contentLoaded
    -0.61
     relâche
    -0.56
    ندية
    -0.53
     "..\..\
    -0.53
     alternately
    -0.52
    Хьажоргаш
    -0.51
    TintMode
    -0.50
     typelib
    -0.49
    POSITIVE LOGITS
     sure
    0.71
     allowed
    0.59
     alone
    0.57
     bothered
    0.57
     fooled
    0.56
    ไหน
    0.55
    sure
    0.54
    logrus
    0.54
     daft
    0.54
    ICING
    0.53
    Act Density 0.131%

    No Known Activations