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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate recommendation or implication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozor
    -0.15
    icky
    -0.15
    é½IJ
    -0.14
    声ãĤĴ
    -0.14
     Sally
    -0.14
    abyrinth
    -0.14
     tiener
    -0.14
    acin
    -0.14
    ACK
    -0.14
    YSIS
    -0.14
    POSITIVE LOGITS
    ipes
    0.16
    ries
    0.15
     Cros
    0.15
    strup
    0.15
    iler
    0.15
     Blues
    0.15
    inger
    0.14
    ÙİØŃ
    0.14
     Batt
    0.14
    mie
    0.14
    Act Density 0.075%

    No Known Activations