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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Podesta
    -0.19
    gabe
    -0.15
    алÑĮ
    -0.14
    :
    -0.14
     Glo
    -0.13
     plain
    -0.13
    ÅĦ
    -0.13
     Gallagher
    -0.13
    oud
    -0.13
    ÑģÑı
    -0.13
    POSITIVE LOGITS
    rollo
    0.17
    одÑĥ
    0.15
    ernals
    0.15
    alnız
    0.15
    èĭ¦
    0.14
    omon
    0.14
    QueryParam
    0.14
    ugins
    0.14
    .native
    0.14
    addError
    0.14
    Act Density 38.741%

    No Known Activations