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

    Neuronpedia

    INDEX
    Explanations

    elements related to identity or personal attributes

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

    Follows dialogue or a question

    np_acts-logits-general · gemini-2.0-flash

    Well, Okay, Yes, judge, Prior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.09
    ()?;
    -0.99
    .";
    -0.98
     فريبيس
    -0.96
    =?";
    -0.94
    )";
    -0.94
     ſind
    -0.93
    ✨:
    -0.92
    ".
    -0.91
    %";
    -0.90
    POSITIVE LOGITS
     I
    0.84
     you
    0.66
    !
    0.64
    .
    0.63
     [
    0.62
    I
    0.61
    ,
    0.60
     he
    0.59
     (
    0.58
     because
    0.53
    Act Density 0.155%

    No Known Activations