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

    Neuronpedia

    INDEX
    Explanations

    references to specific authors or contributors, often in a scholarly context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.82
     nakalista
    -0.80
     '\\;'
    -0.79
    MENAFN
    -0.78
    aarrggbb
    -0.77
    XmlAccessType
    -0.75
     TextAppearance
    -0.74
     BorderSide
    -0.73
    enumii
    -0.72
    OGND
    -0.72
    POSITIVE LOGITS
     W
    0.83
     Wach
    0.77
    wo
    0.76
     WAC
    0.74
     Warriors
    0.70
    W
    0.69
    первых
    0.69
    WO
    0.69
    WTS
    0.69
     Words
    0.68
    Act Density 0.901%

    No Known Activations