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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity or questioning thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.73
     Astoria
    -0.72
    aroa
    -0.71
    %
    -0.70
    caloosa
    -0.65
    IRQn
    -0.62
     receive
    -0.61
     Alba
    -0.58
     Alec
    -0.58
    ibatis
    -0.57
    POSITIVE LOGITS
     wonder
    1.95
     Wonder
    1.90
     wondering
    1.87
    wonder
    1.86
    Wonder
    1.82
     WONDER
    1.74
     wondered
    1.64
     wonders
    1.57
    Wondering
    1.55
     Wonders
    1.45
    Act Density 0.056%

    No Known Activations