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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "write" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the act of writing

    np_acts-logits-general · gemini-2.0-flash

    write and its forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kang
    -0.53
    )++;
    -0.52
     WELFARE
    -0.51
    anema
    -0.51
     Trop
    -0.51
    parsedMessage
    -0.50
     Gap
    -0.50
    amboo
    -0.50
    uzu
    -0.50
     Belf
    -0.49
    POSITIVE LOGITS
     write
    1.73
    write
    1.66
    Write
    1.55
     Write
    1.55
     writing
    1.54
     Writing
    1.38
    writing
    1.36
    Writing
    1.36
     writes
    1.34
     wrote
    1.30
    Act Density 0.101%

    No Known Activations