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

    Neuronpedia

    INDEX
    Explanations

    phrases denoting emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    references to abstract concepts or ideas, particularly those expressed with the character 'âĢĶ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     commun
    -0.78
    perate
    -0.76
    ieth
    -0.74
    worms
    -0.73
    ordinate
    -0.71
    erald
    -0.68
    uder
    -0.67
    uminati
    -0.67
    reens
    -0.67
    illance
    -0.67
    POSITIVE LOGITS
    ————————
    1.69
    ————
    1.63
    ————————————————
    1.35
    ——
    0.93
    _-
    0.90
    particularly
    0.80
    especially
    0.78
    âĢķ
    0.76
    perhaps
    0.76
    ––
    0.75
    Act Density 0.127%

    No Known Activations