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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and expressions reflecting user interactions or sentiments

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

    Followed by questions or personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    the question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.59
    RenderAtEndOf
    -0.59
    Архівовано
    -0.57
    zzleHttp
    -0.56
    ritzau
    -0.56
     TAMBÉM
    -0.55
     OnInit
    -0.55
    etheless
    -0.54
    ~*~
    -0.54
    aarrggbb
    -0.54
    POSITIVE LOGITS
    I
    0.77
    ↵↵
    0.74
    Well
    0.68
    What
    0.68
    The
    0.68
    <h1>
    0.68
     I
    0.67
    قایناقلار
    0.67
    ↵
    0.66
    This
    0.66
    Act Density 0.162%

    No Known Activations