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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ReturnType
    -0.17
    Updates
    -0.16
    ader
    -0.15
    se
    -0.15
     çī
    -0.15
     cách
    -0.15
    enny
    -0.15
    ully
    -0.14
    æĺİ
    -0.14
    θα
    -0.14
    POSITIVE LOGITS
     liners
    0.20
    hell
    0.17
     hell
    0.17
    -nil
    0.17
    jeme
    0.16
    toolbox
    0.15
    -hit
    0.15
    ziej
    0.15
     Hell
    0.15
    ÅĻÃŃzenÃŃ
    0.15
    Act Density 0.055%

    No Known Activations