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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or topics indicated by specific tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -1.10
    Tikang
    -1.02
     المعيارى
    -1.01
     AssemblyTitle
    -0.99
     MessageBoxIcon
    -0.98
    NUMX
    -0.98
     gawas
    -0.95
     lenker
    -0.94
    parsedMessage
    -0.92
    complexContent
    -0.92
    POSITIVE LOGITS
    *
    1.15
     *
    1.02
    *.
    0.76
    <blockquote>
    0.76
    *)
    0.74
    ))*
    0.72
    [toxicity=0]
    0.70
    *,
    0.70
    *:
    0.69
    <eos>
    0.68
    Act Density 0.089%

    No Known Activations