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

    Neuronpedia

    INDEX
    Explanations

    frequent interjections and expressions of excitement or emphasis

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

    application to build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.44
    tanleria
    -0.42
    BagConstraints
    -0.39
     spot
    -0.35
     :-)
    -0.35
    :-)
    -0.35
     Wicidata
    -0.35
     ;-)
    -0.35
    ;-)
    -0.35
    hetically
    -0.33
    POSITIVE LOGITS
    0.57
    ⤹
    0.52
     aapt
    0.50
    httphttps
    0.50
    articolo
    0.49
    RenderAtEndOf
    0.49
    Personendaten
    0.49
    StoryboardSegue
    0.48
     faccia
    0.48
     Amino
    0.48
    Act Density 0.002%

    No Known Activations