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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that introduce exceptions

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

    Followed by a conditional statement

    np_acts-logits-general · gemini-2.0-flash

    unless followed by an exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endphp
    -0.91
     وتسجيلات
    -0.90
    /***/
    -0.80
     fhould
    -0.80
     Majefty
    -0.80
     thofe
    -0.77
    WithIOException
    -0.75
    IntoConstraints
    -0.74
     pleaf
    -0.73
     quæ
    -0.72
    POSITIVE LOGITS
     unless
    0.86
     Unless
    0.75
    unless
    0.73
    Unless
    0.70
     Bres
    0.63
    besch
    0.61
    ereco
    0.61
    Bres
    0.59
     дописавши
    0.58
     hela
    0.56
    Act Density 0.060%

    No Known Activations