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

    Neuronpedia

    INDEX
    Explanations

    requirements for student applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    347
    -0.17
    antro
    -0.15
    intl
    -0.15
    ables
    -0.15
     flows
    -0.14
    pler
    -0.14
    indre
    -0.14
    iaux
    -0.13
    uent
    -0.13
    alus
    -0.13
    POSITIVE LOGITS
    APH
    0.17
    æĶ¯
    0.16
     Rack
    0.14
    ç¨ĭ
    0.14
    Cancelable
    0.14
    /console
    0.14
     aph
    0.14
    tility
    0.14
    egra
    0.14
    æĪĸ
    0.14
    Act Density 0.055%

    No Known Activations