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

    Neuronpedia

    INDEX
    Explanations

    words related to writing or composing text

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.84
    ega
    -0.78
    EGA
    -0.77
    rolet
    -0.75
    abe
    -0.75
    alo
    -0.72
    Afee
    -0.68
    Magn
    -0.66
    agara
    -0.66
    nel
    -0.65
    POSITIVE LOGITS
     poems
    0.85
     penned
    0.84
    smanship
    0.84
    writing
    0.78
     notebook
    0.76
     essays
    0.75
     letters
    0.74
    writer
    0.74
     poem
    0.74
     writing
    0.74
    Act Density 0.036%

    No Known Activations