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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "appear."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "appear" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dp
    -0.77
    aign
    -0.66
    Ws
    -0.65
    rpm
    -0.64
    shaw
    -0.64
     Mahjong
    -0.64
    ses
    -0.61
     Haram
    -0.59
    warts
    -0.59
    iott
    -0.59
    POSITIVE LOGITS
     onstage
    0.97
     alongside
    0.82
     poised
    0.79
     briefly
    0.78
     prominently
    0.76
    united
    0.75
    vind
    0.72
     victorious
    0.71
     intoxicated
    0.71
     beside
    0.69
    Act Density 0.043%

    No Known Activations