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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong emotional reactions or confrontational statements

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

    expressions of affirmation or confirmation in statements

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

    English punctuation and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NTSTATUS
    -0.54
    ()?;
    -0.53
     Pri
    -0.52
    Pri
    -0.50
     daß
    -0.50
    のだろう
    -0.49
     />';
    -0.48
    ylabel
    -0.47
     Incluso
    -0.47
    而在
    -0.46
    POSITIVE LOGITS
    yntaxException
    0.82
    StoryboardSegue
    0.80
     yeah
    0.74
     alright
    0.73
    expandindo
    0.72
     Alright
    0.71
     myſelf
    0.70
     reaſon
    0.68
     pleaſure
    0.68
     purpoſe
    0.68
    Act Density 0.034%

    No Known Activations