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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "write" and its variations indicating the act of writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.91
    unhofer
    -0.90
     resourceCulture
    -0.76
    arResult
    -0.75
     Савезне
    -0.75
    favicon
    -0.75
     *)&
    -0.74
    prilis
    -0.73
    bundes
    -0.72
     Bef
    -0.72
    POSITIVE LOGITS
     writing
    1.58
     write
    1.55
    write
    1.50
     Writing
    1.42
     wrote
    1.40
     writes
    1.37
     WRITE
    1.36
     WRITING
    1.36
    Writing
    1.36
    Write
    1.33
    Act Density 0.124%

    No Known Activations