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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks and specific formatting characters in a code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bates
    -0.15
     remaining
    -0.14
     pron
    -0.14
     babys
    -0.14
    laughter
    -0.14
    PG
    -0.14
    Ãłi
    -0.14
    гл
    -0.13
    lico
    -0.13
    ли
    -0.13
    POSITIVE LOGITS
     break
    0.39
    break
    0.35
    	break
    0.34
    -break
    0.32
     breaks
    0.28
     Break
    0.27
    _break
    0.26
    Break
    0.26
     brake
    0.25
    ;break
    0.25
    Act Density 0.030%

    No Known Activations