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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "write" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "write" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.81
     Shinra
    -0.78
    Enlarge
    -0.77
    EGA
    -0.72
    Ton
    -0.71
    xon
    -0.70
    Magn
    -0.69
     ILCS
    -0.68
     Amph
    -0.67
    Fram
    -0.67
    POSITIVE LOGITS
    Write
    0.89
     write
    0.89
    write
    0.89
    smanship
    0.89
    yright
    0.85
    writers
    0.81
     poems
    0.80
     scrib
    0.79
    lishing
    0.79
    writing
    0.79
    Act Density 0.013%

    No Known Activations