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

    Neuronpedia

    INDEX
    Explanations

    references to GitHub links or related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wig
    -0.16
    enes
    -0.16
    alie
    -0.16
    hton
    -0.15
    imar
    -0.14
    yx
    -0.14
    itu
    -0.14
    ither
    -0.14
    bearing
    -0.14
    ithe
    -0.14
    POSITIVE LOGITS
    lette
    0.15
    okrat
    0.14
    zeug
    0.14
    ãĥģãĥ¥
    0.14
    ξÏį
    0.14
    ovat
    0.14
    nett
    0.14
     ëĤĺê°Ģ
    0.13
    achi
    0.13
    UNT
    0.13
    Act Density 0.002%

    No Known Activations