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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "through."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rypto
    -0.15
    abyrin
    -0.14
    aken
    -0.14
    urve
    -0.14
    agon
    -0.14
    аÑĢаÑĤ
    -0.14
    rych
    -0.14
    ursal
    -0.13
    δεÏĤ
    -0.13
    .wp
    -0.13
    POSITIVE LOGITS
    put
    0.23
    puts
    0.22
    s
    0.20
    bred
    0.18
    ought
    0.18
    ough
    0.17
    ou
    0.16
    reesome
    0.16
    -out
    0.15
    -pro
    0.15
    Act Density 0.067%

    No Known Activations