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

    Neuronpedia

    INDEX
    Explanations

    references to web-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     safety
    -0.15
    ä¸įåIJĮ
    -0.14
     different
    -0.13
    شد
    -0.13
    _DECLARE
    -0.13
     Safety
    -0.13
    fers
    -0.13
     extent
    -0.13
    enk
    -0.13
     Moss
    -0.13
    POSITIVE LOGITS
    нен
    0.16
     gam
    0.15
    ittal
    0.15
    halt
    0.14
     اج
    0.14
     Vide
    0.14
    .GPIO
    0.14
    IRA
    0.14
    .executor
    0.14
    Extras
    0.14
    Act Density 0.178%

    No Known Activations