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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.68
    '],
    -0.61
    AddHtmlAttribute
    -0.54
    EndContext
    -0.54
    ărilor
    -0.53
    "]);
    -0.52
    //
    -0.49
    ślę
    -0.49
     foon
    -0.49
    })->
    -0.48
    POSITIVE LOGITS
    ?!
    0.77
    !?
    0.69
    !
    0.67
    DoubleQuotes
    0.65
    ?!?
    0.65
    竟然是
    0.64
    ?!?!
    0.63
    fjspx
    0.63
    rungsseite
    0.62
    竟然
    0.61
    Act Density 0.133%

    No Known Activations