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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "write" and its variations

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

    verbs for writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.76
     Jefus
    -0.62
     myſelf
    -0.55
    PMailer
    -0.53
     becauſe
    -0.52
     Houſe
    -0.52
     againſt
    -0.47
     pleaſure
    -0.45
     poffe
    -0.44
     itſelf
    -0.44
    POSITIVE LOGITS
     wrote
    0.80
     writes
    0.78
     write
    0.71
     Writes
    0.62
     skriver
    0.60
     scrive
    0.59
     Wrote
    0.59
    wrote
    0.59
     نوشت
    0.58
     writing
    0.57
    Act Density 0.017%

    No Known Activations