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

    Neuronpedia

    INDEX
    Explanations

    Repetitive patterns with punctuation marks such as sequences of periods

    oai_token-act-pair · gpt-3.5-turbo

    the presence of punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ´
    -0.62
    éĹĺ
    -0.61
    agher
    -0.60
     hospitality
    -0.59
    ãĥ¼ãĥĨ
    -0.59
     elector
    -0.58
     primaries
    -0.58
     supplements
    -0.56
     legends
    -0.55
     caps
    -0.55
    POSITIVE LOGITS
     ."
    1.06
     .)
    0.84
    \-
    0.81
    mil
    0.80
    turn
    0.79
    -.
    0.78
    Roberts
    0.76
     .
    0.74
    ::::::::
    0.74
     ..
    0.74
    Act Density 0.028%

    No Known Activations