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

    Neuronpedia

    INDEX
    Explanations

    the character 'ķ' in a document

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols that appear frequently in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arios
    -0.74
     prefrontal
    -0.72
    ufact
    -0.72
     gestation
    -0.72
     inertia
    -0.68
     Nadu
    -0.67
     logger
    -0.66
     Aber
    -0.65
     narrowly
    -0.65
    iasm
    -0.65
    POSITIVE LOGITS
    ¾
    0.93
    Ĭ
    0.93
    Ķ
    0.91
    ij
    0.86
    Column
    0.86
    İ
    0.85
    Ĩ
    0.84
    flush
    0.84
    ा
    0.83
    à¥
    0.82
    Act Density 0.006%

    No Known Activations