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

    Neuronpedia

    INDEX
    Explanations

    instances where the action of "turning" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "turn" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.96
    ropolitan
    -0.79
    capacity
    -0.75
    ording
    -0.67
    mma
    -0.66
    inately
    -0.66
    foundation
    -0.63
    bour
    -0.62
     Colleg
    -0.62
    assment
    -0.61
    POSITIVE LOGITS
     into
    0.76
     awa
    0.76
    coat
    0.75
    agra
    0.73
     inward
    0.69
    around
    0.68
     shif
    0.67
    Ĺ
    0.67
    about
    0.67
     sour
    0.66
    Act Density 0.038%

    No Known Activations