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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases that indicate exceptions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unknow
    -0.15
     Partners
    -0.14
    rss
    -0.14
    omap
    -0.13
    una
    -0.13
    Ỽ
    -0.13
    .toInt
    -0.13
    ToolStrip
    -0.13
    shan
    -0.13
     Haz
    -0.13
    POSITIVE LOGITS
     necessarily
    0.19
    ITU
    0.15
    ches
    0.15
    much
    0.15
    оÑĢи
    0.14
    ductor
    0.14
    ori
    0.14
    eur
    0.14
    abwe
    0.14
    :///
    0.13
    Act Density 0.097%

    No Known Activations