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

    Neuronpedia

    INDEX
    Explanations

    references to the writing and publishing process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olta
    -0.18
    gili
    -0.16
    .Raise
    -0.15
    azon
    -0.15
    iqueta
    -0.14
    ilden
    -0.14
    ög
    -0.14
    ÅĽnie
    -0.13
    ackson
    -0.13
    oux
    -0.13
    POSITIVE LOGITS
     rough
    0.47
     draft
    0.46
     finished
    0.39
     drafts
    0.38
     Rough
    0.37
    draft
    0.36
    rough
    0.35
     Draft
    0.34
     completed
    0.33
    Draft
    0.33
    Act Density 0.267%

    No Known Activations