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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly colons, and their usage in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unic
    -0.17
     Towers
    -0.15
    oblins
    -0.14
    lical
    -0.14
    uš
    -0.14
    lico
    -0.14
    ahan
    -0.13
    lassen
    -0.13
    reas
    -0.13
    otec
    -0.13
    POSITIVE LOGITS
    347
    0.15
     Glob
    0.15
    hai
    0.15
    ager
    0.14
    891
    0.14
    egie
    0.14
     Parr
    0.14
    าà¸ĺ
    0.14
    wear
    0.14
    357
    0.14
    Act Density 0.001%

    No Known Activations