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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iola
    -0.16
    TEGER
    -0.15
    rena
    -0.15
    igo
    -0.15
    ModuleName
    -0.14
    canf
    -0.14
    antly
    -0.14
    woff
    -0.14
    istes
    -0.14
    .vertx
    -0.14
    POSITIVE LOGITS
     Downs
    0.16
     gre
    0.16
     Gre
    0.14
    Gre
    0.14
    ubo
    0.14
     swingers
    0.14
    ery
    0.14
    uchar
    0.14
    ÑĢаÑĩ
    0.14
     configurable
    0.13
    Act Density 0.294%

    No Known Activations