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

    Neuronpedia

    INDEX
    Explanations

    short, often two-letter CamelCase or capitalized fragments within proper names, acronyms, and code identifiers.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    每当
    -0.07
    getting
    -0.07
    Father
    -0.07
     bans
    -0.06
    generated
    -0.06
    ceptions
    -0.06
     saldır
    -0.06
     che
    -0.06
    oto
    -0.06
    不可
    -0.06
    POSITIVE LOGITS
     calorie
    0.08
    .What
    0.07
     TMP
    0.07
    ITIZE
    0.07
    Factors
    0.07
     questioned
    0.07
     compiling
    0.07
    -Class
    0.07
    _barrier
    0.07
    _mc
    0.06
    Act Density 0.208%

    No Known Activations