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

    Neuronpedia

    INDEX
    Explanations

    frequent conversational prompts and expressions of curiosity or concern

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

    I followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ayrıca
    -0.45
     preguntar
    -0.43
     accordingly
    -0.42
     also
    -0.42
    intervento
    -0.41
     spørgsmål
    -0.40
     sveta
    -0.40
     meliputi
    -0.40
     passagem
    -0.40
    angaben
    -0.39
    POSITIVE LOGITS
     Administrativna
    0.72
     كومونز
    0.63
    évaluateur
    0.60
    GEBURTSDATUM
    0.60
    WebElementEntity
    0.60
    reportWebVitals
    0.57
     pleaſure
    0.57
    Personendaten
    0.56
    __(/*!
    0.56
     ویکی‌پدی
    0.54
    Act Density 0.042%

    No Known Activations