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

    Neuronpedia

    INDEX
    Explanations

    phrases showing curiosity and inquiry about character development

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

    what might happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.63
     ModelExpression
    -0.61
     Lordships
    -0.59
    coders
    -0.57
    actéristi
    -0.56
    <unused8>
    -0.56
    <unused41>
    -0.56
    [@BOS@]
    -0.56
    <unused16>
    -0.55
    <unused17>
    -0.55
    POSITIVE LOGITS
     plot
    0.42
     maybe
    0.37
     mostrarán
    0.37
     perhaps
    0.35
    Rüyada
    0.34
     will
    0.33
     possibly
    0.33
     Plot
    0.33
    :][
    0.30
     subplot
    0.30
    Act Density 0.008%

    No Known Activations