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

    Neuronpedia

    INDEX
    Explanations

    words related to writing and documenting activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "write."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.83
     Shinra
    -0.78
    Magn
    -0.73
     ILCS
    -0.71
    EGA
    -0.70
    eger
    -0.69
    Enlarge
    -0.69
    Unity
    -0.68
    azar
    -0.67
     Unsure
    -0.66
    POSITIVE LOGITS
    smanship
    0.85
     poems
    0.82
    manship
    0.81
    write
    0.80
    writer
    0.80
    lishing
    0.78
    writing
    0.77
    writers
    0.76
     poem
    0.76
     write
    0.75
    Act Density 0.034%

    No Known Activations