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

    Neuronpedia

    INDEX
    Explanations

    sequences of punctuation that may signal a transition or emphasis in the text

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¼
    -0.68
     infl
    -0.67
    GN
    -0.63
    enta
    -0.62
    ighter
    -0.62
    ãĥ´
    -0.61
     overs
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.59
    mith
    -0.59
     fixture
    -0.58
    POSITIVE LOGITS
    selves
    0.86
    until
    0.84
     ."
    0.84
    shall
    0.82
    relevant
    0.71
     Oops
    0.71
    SIGN
    0.70
    FORE
    0.69
    mil
    0.69
    carry
    0.65
    Act Density 0.016%

    No Known Activations