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

    Neuronpedia

    INDEX
    Explanations

    references to input fields and their attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ey
    -0.17
    iras
    -0.16
    ings
    -0.16
    æĸ¹
    -0.15
    ufen
    -0.14
    alie
    -0.14
    lord
    -0.14
    trees
    -0.14
    ieur
    -0.14
    ivic
    -0.14
    POSITIVE LOGITS
    orp
    0.18
    rette
    0.15
    áze
    0.15
     horizon
    0.14
    ÑĬ
    0.14
    etik
    0.14
    DDR
    0.14
    yonel
    0.13
    385
    0.13
    _BOOT
    0.13
    Act Density 0.006%

    No Known Activations