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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation, particularly those indicating data structure or separation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RetentionPolicy
    -0.56
    LookAnd
    -0.55
     Dinah
    -0.50
    Resin
    -0.49
     vitre
    -0.47
    /$',
    -0.47
    $/,
    -0.47
    luents
    -0.47
    essica
    -0.46
    antle
    -0.46
    POSITIVE LOGITS
     مرئيه
    0.92
     Vikipedi
    0.82
     doInBackground
    0.65
     “…
    0.64
     (…)
    0.64
    elemField
    0.62
    DockStyle
    0.62
     (...)
    0.61
    “…
    0.60
     &___
    0.59
    Act Density 0.180%

    No Known Activations