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

    Neuronpedia

    INDEX
    Explanations

    HTML or JavaScript document types and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mb
    -0.14
    opolitan
    -0.14
    amed
    -0.14
    este
    -0.14
    alls
    -0.14
    δο
    -0.13
    zych
    -0.13
    elig
    -0.13
    aget
    -0.13
    [section
    -0.13
    POSITIVE LOGITS
    faces
    0.17
    tep
    0.16
     Former
    0.16
    face
    0.15
    ="
    0.15
    826
    0.14
     posterior
    0.14
    å½Ĵ
    0.14
    yz
    0.14
    uru
    0.14
    Act Density 0.017%

    No Known Activations