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

    Neuronpedia

    INDEX
    Explanations

    expressions of skepticism or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    doubt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CodeAttribute
    -0.56
     <<<<<<<<<<<<<<
    -0.54
     InputDecoration
    -0.53
     للاسماء
    -0.47
    就是要
    -0.47
    majánló
    -0.46
     ब्रेकडाउन
    -0.46
    Handlung
    -0.45
    omena
    -0.45
    AddTagHelper
    -0.45
    POSITIVE LOGITS
     doubted
    0.66
    Doubt
    0.61
     Doubt
    0.59
     doubtful
    0.57
     doubt
    0.52
    doubt
    0.52
     unlikely
    0.50
     Hardly
    0.50
     neither
    0.48
     doubting
    0.47
    Act Density 0.009%

    No Known Activations