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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "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
    emies
    -0.85
    ammers
    -0.79
    zos
    -0.79
    enegger
    -0.76
    inders
    -0.76
    older
    -0.74
    ortunately
    -0.73
    thumbnails
    -0.72
    ãĤ¤ãĥĪ
    -0.72
    needs
    -0.69
    POSITIVE LOGITS
     instance
    0.93
     embodiment
    0.88
     iteration
    0.88
     hundred
    0.87
     stroke
    0.85
     episode
    0.79
     occasion
    0.78
     corner
    0.76
     memorable
    0.74
     hand
    0.74
    Act Density 0.047%

    No Known Activations