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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and commands

    oai_token-act-pair · gpt-3.5-turbo

    the presence of empty text segments or breaks in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jit
    -0.72
    Said
    -0.67
    ¬¼
    -0.67
    minster
    -0.65
    aha
    -0.63
    zar
    -0.62
    Cru
    -0.62
    Kind
    -0.62
    Favorite
    -0.62
    closure
    -0.61
    POSITIVE LOGITS
     please
    0.98
     however
    0.87
     proceed
    0.86
     chances
    0.85
     congratulations
    0.83
     then
    0.82
     choose
    0.79
     whichever
    0.79
     you
    0.79
    please
    0.76
    Act Density 0.233%

    No Known Activations