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

    Neuronpedia

    INDEX
    Explanations

    references to drafts and manuscripts in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gies
    -0.74
    cmath
    -0.71
    FIG
    -0.69
    beh
    -0.68
     bi
    -0.67
    [:,
    -0.67
    oblastoma
    -0.66
    secta
    -0.65
    skechers
    -0.65
    ism
    -0.64
    POSITIVE LOGITS
     drafts
    1.27
     draft
    1.24
    draft
    1.18
     DRAFT
    1.15
     Draft
    1.13
    DRAFT
    1.10
    Draft
    1.06
     drafted
    1.04
     ballast
    0.87
    rafts
    0.86
    Act Density 0.107%

    No Known Activations