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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NVIC
    -0.53
     насељу
    -0.48
    drawiam
    -0.46
     normal
    -0.45
    ectady
    -0.43
    !).
    -0.42
    fromnode
    -0.42
    '].
    -0.42
    ++]=
    -0.42
    zeń
    -0.41
    POSITIVE LOGITS
     but
    1.01
     nhưng
    0.84
    but
    0.78
     tetapi
    0.73
     tapi
    0.72
    But
    0.71
     But
    0.68
     namun
    0.68
     kasarigan
    0.66
    RSpec
    0.65
    Act Density 0.381%

    No Known Activations