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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly those related to quantity and frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansi
    -0.15
    oden
    -0.14
    lik
    -0.14
    ascar
    -0.13
    wik
    -0.13
    .bpm
    -0.13
    .VisualBasic
    -0.13
    зÑĥ
    -0.13
    eyh
    -0.12
     rinse
    -0.12
    POSITIVE LOGITS
     word
    0.94
     words
    0.87
    word
    0.78
    -word
    0.75
     Word
    0.74
     WORD
    0.73
    words
    0.71
    Word
    0.70
    _word
    0.69
     Words
    0.69
    Act Density 0.257%

    No Known Activations