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

    Neuronpedia

    INDEX
    Explanations

    punctuation and the use of interactive elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gend
    -0.15
    kel
    -0.15
    usch
    -0.14
    kf
    -0.14
    ·
    -0.13
    pcf
    -0.13
    ondheim
    -0.13
     fixing
    -0.13
    lige
    -0.13
    ucks
    -0.13
    POSITIVE LOGITS
    039
    0.19
    ylland
    0.16
    emo
    0.15
     ðŁĺī↵↵
    0.15
    çħ§
    0.15
    Powered
    0.14
     chatte
    0.14
    =>'
    0.14
    ût
    0.14
    93
    0.14
    Act Density 0.004%

    No Known Activations