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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ryn
    -0.15
    uste
    -0.14
    _WRAP
    -0.14
     kaf
    -0.14
    èĴĤ
    -0.14
    redient
    -0.13
    coholic
    -0.13
    .wrap
    -0.13
    olecule
    -0.13
     Mos
    -0.13
    POSITIVE LOGITS
    ILES
    0.16
    boxed
    0.15
    ysize
    0.15
    çĽĹ
    0.14
    à¹ģà¸Ļ
    0.13
    ÙĨÙĬØ©
    0.13
    isch
    0.13
    _codegen
    0.13
    verty
    0.13
    RTC
    0.13
    Act Density 0.006%

    No Known Activations