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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and statistics related to research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëĶ
    -0.17
    湯
    -0.17
    krom
    -0.15
    ãĥ«ãĤ¯
    -0.15
    etter
    -0.15
    eldon
    -0.15
    abled
    -0.14
    auen
    -0.14
    _costs
    -0.14
    権
    -0.14
    POSITIVE LOGITS
    ewing
    0.15
    sth
    0.15
    JD
    0.15
    ÑĢек
    0.14
     Vital
    0.14
     Ramp
    0.14
     ha
    0.14
    orp
    0.14
     år
    0.13
    ÑĨÑĮ
    0.13
    Act Density 0.188%

    No Known Activations