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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing uncertainty or bias in opinion

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

    Follows "so" or a comma ", "

    np_acts-logits-general · gemini-2.0-flash

    concluding determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     becauſe
    -0.81
     Efq
    -0.74
     Çünkü
    -0.72
     raiſ
    -0.71
    ClientRect
    -0.69
    posedge
    -0.68
    ::_('
    -0.67
    reportWebVitals
    -0.66
    AddField
    -0.66
     للاسماء
    -0.64
    POSITIVE LOGITS
     naturally
    0.77
    naturally
    0.66
    Naturally
    0.63
    仕方ない
    0.61
     Naturally
    0.60
     forcément
    0.59
     naturellement
    0.57
     unsur
    0.56
     naturalmente
    0.56
     understandably
    0.52
    Act Density 0.435%

    No Known Activations