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

    Neuronpedia

    INDEX
    Explanations

    references to blogging and writing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AU
    -0.15
     Leh
    -0.15
    oler
    -0.15
    ãģĮåĩº
    -0.15
     Personnel
    -0.14
     sam
    -0.14
    atures
    -0.14
     Xu
    -0.14
    [
    -0.14
    ugh
    -0.14
    POSITIVE LOGITS
    eldorf
    0.19
    .documentation
    0.17
    /******/
    0.17
    _here
    0.17
     presente
    0.16
    yk
    0.16
    Collider
    0.16
     aquÃŃ
    0.15
     ÙĩÙĨا
    0.15
    EDITOR
    0.15
    Act Density 0.327%

    No Known Activations