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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or amazement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meri
    -0.61
    erl
    -0.59
     QL
    -0.57
    पया
    -0.56
    sidemargin
    -0.56
     Pel
    -0.55
    子上
    -0.55
     asientos
    -0.55
    uali
    -0.53
    Pel
    -0.53
    POSITIVE LOGITS
     wow
    1.39
     WOW
    1.31
    wow
    1.26
     Wow
    1.25
    Wow
    1.22
    WOW
    1.20
     Jefus
    0.88
     ſhe
    0.87
     Darn
    0.85
     woof
    0.83
    Act Density 0.062%

    No Known Activations