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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences starting with "One."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "One."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.86
    osponsors
    -0.84
    hips
    -0.77
    ="#
    -0.76
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    ÃįÃį
    -0.62
    uits
    -0.62
    respective
    -0.61
    ships
    -0.61
    oof
    -0.60
    POSITIVE LOGITS
     Hundred
    1.11
     hundred
    1.03
     thing
    0.99
     Piece
    0.97
    esan
    0.82
     wonders
    0.80
     Thousand
    0.80
     drawback
    0.79
     Million
    0.79
     reason
    0.78
    Act Density 0.060%

    No Known Activations