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

    Neuronpedia

    INDEX
    Explanations

    statements and expressions of opinions or observations about societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     also
    -0.28
    also
    -0.23
    Also
    -0.23
     ALSO
    -0.22
     Also
    -0.21
     también
    -0.21
     também
    -0.20
     Ø£ÙĬض
    -0.20
     także
    -0.19
     cũng
    -0.19
    POSITIVE LOGITS
     lately
    0.19
     bekl
    0.16
     perhaps
    0.16
    reamble
    0.15
     odds
    0.14
     proverb
    0.14
     probably
    0.14
     pretty
    0.13
     Odds
    0.13
     any
    0.13
    Act Density 0.343%

    No Known Activations