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

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion or uncertainty

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

    "even" and its negative connotations

    np_acts-logits-general · gemini-2.0-flash

    even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtate
    -0.70
    AddHtmlAttribute
    -0.69
     Chriſt
    -0.64
     alſo
    -0.64
     Jefus
    -0.62
     purpoſe
    -0.62
     ſtill
    -0.61
    TagMode
    -0.60
    /**
    -0.60
     ſeveral
    -0.59
    POSITIVE LOGITS
     siquiera
    0.81
     remotely
    0.76
     bother
    0.74
     bothering
    0.72
    binaan
    0.67
     half
    0.65
     bothered
    0.64
     even
    0.64
     barely
    0.57
    影子
    0.54
    Act Density 0.081%

    No Known Activations