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

    Neuronpedia

    INDEX
    Explanations

    references to "through" indicating methods or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rypto
    -0.16
    agon
    -0.15
    ignum
    -0.15
    UNCT
    -0.14
    ursal
    -0.14
    ilitating
    -0.14
    urve
    -0.14
    аÑĢаÑĤ
    -0.14
    abyrin
    -0.13
    еÑĢÑĤа
    -0.13
    POSITIVE LOGITS
    put
    0.22
    puts
    0.22
    s
    0.20
    bred
    0.19
    ought
    0.19
    ou
    0.17
    -out
    0.16
    lined
    0.16
    -pro
    0.16
    ogh
    0.16
    Act Density 0.065%

    No Known Activations