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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ODO
    -0.16
    ellij
    -0.14
    onaut
    -0.14
    cosa
    -0.14
    ÑĢиÑĩ
    -0.13
    ahan
    -0.13
    .wik
    -0.13
    ék
    -0.13
     Dit
    -0.13
    mscorlib
    -0.13
    POSITIVE LOGITS
    (#)
    0.15
    ATORY
    0.15
    aben
    0.15
    readcr
    0.14
     Bolton
    0.14
    ê¸ī
    0.13
    PIC
    0.13
    é¾Ļ
    0.13
    RefPtr
    0.13
    .FAIL
    0.13
    Act Density 0.020%

    No Known Activations