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

    Neuronpedia

    INDEX
    Explanations

    references to control systems and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itä
    -0.16
    reon
    -0.16
    ÑĶм
    -0.15
     heav
    -0.14
     cob
    -0.14
     Libert
    -0.14
    zdy
    -0.14
    etooth
    -0.14
    맥
    -0.13
    kan
    -0.13
    POSITIVE LOGITS
    appropri
    0.16
    iew
    0.15
     appropriate
    0.14
    986
    0.14
    rito
    0.14
    ourse
    0.14
     respective
    0.14
    avo
    0.14
    ble
    0.14
    ornings
    0.13
    Act Density 0.103%

    No Known Activations