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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and acknowledgment for efforts against injustice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acky
    -0.16
    OrElse
    -0.16
    oyer
    -0.15
    clin
    -0.15
    _BIT
    -0.15
    Laughs
    -0.14
    essler
    -0.13
    agma
    -0.13
    oler
    -0.13
    upo
    -0.13
    POSITIVE LOGITS
     Bravo
    0.34
     credit
    0.29
     Hats
    0.28
     hats
    0.28
     props
    0.27
     Props
    0.27
    Props
    0.26
    udos
    0.25
     Credit
    0.24
    credit
    0.23
    Act Density 0.030%

    No Known Activations