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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or text patterns

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the symbol "âĢĶ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    worms
    -0.80
     commun
    -0.79
    perate
    -0.75
    ieth
    -0.75
    uder
    -0.73
    ifi
    -0.71
    erald
    -0.71
    iple
    -0.70
    ordinate
    -0.70
    aimon
    -0.69
    POSITIVE LOGITS
    ————————
    1.71
    ————
    1.67
    ————————————————
    1.35
    ——
    1.02
    _-
    0.82
    ––
    0.80
    âĢķ
    0.78
    particularly
    0.73
    —-
    0.71
     Kimber
    0.70
    Act Density 0.123%

    No Known Activations