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

    Neuronpedia

    INDEX
    Explanations

    exclamatory punctuation marks

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

    exclamations and emphasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jereo
    -0.47
    httphttps
    -0.41
    Rohy
    -0.40
     محفوظة
    -0.40
     Roskov
    -0.35
     amikor
    -0.33
    mení
    -0.33
     kili
    -0.33
    mtd
    -0.32
     plead
    -0.32
    POSITIVE LOGITS
    !
    0.71
    !..
    0.65
    ]!
    0.63
    .!
    0.61
    !...
    0.60
    !.
    0.60
    !*
    0.60
    !!!!!!
    0.60
    !!!
    0.59
    )!
    0.58
    Act Density 0.029%

    No Known Activations