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

    Neuronpedia

    INDEX
    Explanations

    characters representing special characters and some programming-related sequences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.83
    ometimes
    -0.82
    conservancy
    -0.80
     corrid
    -0.80
     behavi
    -0.80
     citiz
    -0.78
     footing
    -0.76
    chwitz
    -0.76
    everal
    -0.76
    natureconservancy
    -0.72
    POSITIVE LOGITS
     etc
    1.01
     Jr
    0.85
     et
    0.81
     supra
    0.79
    esp
    0.74
    000
    0.71
     huh
    0.70
     pp
    0.70
     eh
    0.70
    001
    0.69
    Act Density 1.223%

    No Known Activations