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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks used in programming syntax

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     just
    -0.50
    хар
    -0.46
     h
    -0.41
    just
    -0.41
    Anything
    -0.40
     certainly
    -0.40
     kort
    -0.39
     Hef
    -0.38
     tunggal
    -0.38
     Anything
    -0.37
    POSITIVE LOGITS
     متعلقه
    1.13
     للمعارف
    1.13
    UserScript
    1.06
    ंदीखरीदारी
    0.93
     محفوظة
    0.92
    脚注の使い方
    0.91
    expandindo
    0.91
    __':
    0.88
    AndEndTag
    0.87
    __":
    0.87
    Act Density 0.008%

    No Known Activations