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

    Neuronpedia

    INDEX
    Explanations

    occurrences of file source references or paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sprüche
    -0.53
    ########.
    -0.50
    اریخ
    -0.49
     counter
    -0.48
    rents
    -0.46
    phins
    -0.46
     resourceCulture
    -0.46
    ardians
    -0.45
    xyl
    -0.45
     проти
    -0.45
    POSITIVE LOGITS
     usual
    0.66
    Usual
    0.66
    usual
    0.63
     preserved
    0.62
     Usual
    0.57
    IOException
    0.57
    src
    0.52
    HtmlAttribute
    0.50
    preserved
    0.50
    onload
    0.45
    Act Density 0.305%

    No Known Activations