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

    Neuronpedia

    INDEX
    Explanations

    patterns involving counter manipulations and repetitive code structures

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.80
    Skocz
    -0.78
    aarrggbb
    -0.65
    ynb
    -0.65
     toimi
    -0.62
     Réponses
    -0.60
     صوتيه
    -0.60
    endregion
    -0.59
    Референце
    -0.59
     &___
    -0.59
    POSITIVE LOGITS
    Counter
    1.63
    counter
    1.38
    COUNTER
    1.25
     Counter
    1.10
     counterfeit
    0.80
     COUNTER
    0.78
     counterfe
    0.72
    counters
    0.56
    cntr
    0.55
     disambiguazione
    0.53
    Act Density 0.002%

    No Known Activations