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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Power"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Power."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seq
    -0.69
    ãĤ¢ãĥ«
    -0.67
    arians
    -0.66
    ×IJ
    -0.65
     Bei
    -0.65
    oslov
    -0.64
    ãģĵ
    -0.63
    âĸ¬âĸ¬
    -0.62
    keyes
    -0.62
    ATIONAL
    -0.62
    POSITIVE LOGITS
    houses
    0.84
     Grid
    0.84
    puff
    0.80
    bilt
    0.80
     Rangers
    0.80
    wash
    0.78
    stroke
    0.78
    ball
    0.78
    lifting
    0.76
    lad
    0.75
    Act Density 0.020%

    No Known Activations