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

    Neuronpedia

    INDEX
    Explanations

    function declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iture
    -0.16
    ’t
    -0.14
    ../
    -0.14
    ESSAGES
    -0.14
    vinces
    -0.14
    lj
    -0.13
    å¤īãĤı
    -0.13
    odal
    -0.13
    ancia
    -0.13
    sey
    -0.13
    POSITIVE LOGITS
    ctrine
    0.18
    curring
    0.18
    206
    0.17
    imity
    0.17
    sense
    0.17
    s
    0.16
    zeit
    0.15
    yaw
    0.15
    suit
    0.14
    ing
    0.14
    Act Density 0.078%

    No Known Activations