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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and words that indicate contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hummel
    -0.53
    multirow
    -0.51
    D
    -0.49
    Escape
    -0.47
    న్న
    -0.46
    Mason
    -0.46
    setCancelable
    -0.46
     Tiberius
    -0.46
    C
    -0.46
    ütün
    -0.45
    POSITIVE LOGITS
    NameInMap
    0.86
    rungsseite
    0.85
     lenker
    0.77
    aarrggbb
    0.77
     cherchés
    0.74
     simply
    0.73
    Enllaces
    0.72
     дописавши
    0.72
    ArrowToggle
    0.70
    :");
    0.67
    Act Density 0.142%

    No Known Activations