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

    Neuronpedia

    INDEX
    Explanations

    words indicating causation or reason

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "So" used to make transitions or conclusions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    saf
    -0.71
    thro
    -0.67
     ``(
    -0.63
    ¢
    -0.62
    exclusive
    -0.62
     Â
    -0.59
    '';
    -0.56
    ASED
    -0.56
    sk
    -0.55
     Scand
    -0.55
    POSITIVE LOGITS
    oner
    1.26
    bered
    1.00
    fter
    0.98
    apy
    0.95
    othes
    0.94
    FTWARE
    0.94
    oths
    0.85
    ooo
    0.84
    othe
    0.84
    aps
    0.84
    Act Density 0.055%

    No Known Activations