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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.76
     Astoria
    -0.67
    paksa
    -0.63
    IRQn
    -0.62
     Alba
    -0.61
    caloosa
    -0.60
    aroa
    -0.60
     alba
    -0.57
    vajal
    -0.56
     Industri
    -0.56
    POSITIVE LOGITS
     wonder
    1.76
     wondering
    1.76
     Wonder
    1.70
    wonder
    1.70
    Wonder
    1.64
     WONDER
    1.61
     wondered
    1.52
    Wondering
    1.40
     wonders
    1.36
     Wonders
    1.28
    Act Density 0.066%

    No Known Activations