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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "write" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.96
    unhofer
    -0.88
     Савезне
    -0.83
    favicon
    -0.77
     Bef
    -0.73
    +#+
    -0.71
    Anastasia
    -0.71
     Barney
    -0.71
    ganggu
    -0.71
    contentLoaded
    -0.70
    POSITIVE LOGITS
     writing
    1.47
     write
    1.40
    write
    1.36
     Writing
    1.33
     wrote
    1.29
     WRITING
    1.29
    Writing
    1.29
     writers
    1.25
     writes
    1.25
     WRITE
    1.25
    Act Density 0.119%

    No Known Activations