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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions implying uncertainty or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quoque
    -0.59
     tambi
    -0.52
     XZ
    -0.52
     Witkin
    -0.51
    сього
    -0.51
    先是
    -0.51
    Beneficios
    -0.50
     sometime
    -0.50
     poivre
    -0.49
    lgari
    -0.49
    POSITIVE LOGITS
     nor
    0.95
    RTDA
    0.95
    AddTagHelper
    0.87
    AndEndTag
    0.86
     оригіналу
    0.85
     necessarily
    0.84
    ArrowToggle
    0.82
     Not
    0.81
    Jeografia
    0.80
     ProtoMessage
    0.80
    Act Density 1.227%

    No Known Activations