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

    Neuronpedia

    INDEX
    Explanations

    numerical values, especially related to quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.19
     actionTypes
    -0.17
    (íģ¬ê¸°
    -0.15
    wend
    -0.15
    orie
    -0.15
     ActionTypes
    -0.15
     tavs
    -0.15
    LC
    -0.14
    uze
    -0.14
    uming
    -0.14
    POSITIVE LOGITS
    0.32
    '
    0.23
    ’
    0.22
    000
    0.18
    \:
    0.17
    Ù¬
    0.17
    Âł
    0.17
    âĢī
    0.15
    ł
    0.15
     oo
    0.15
    Act Density 0.030%

    No Known Activations