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

    Neuronpedia

    INDEX
    Explanations

    words related to paperwork or administrative tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to paperwork and associated tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.78
    oise
    -0.76
    irth
    -0.74
    ideshow
    -0.71
     Subtle
    -0.70
    efully
    -0.70
    olph
    -0.70
    gom
    -0.68
    dden
    -0.67
    arya
    -0.67
    POSITIVE LOGITS
     paperwork
    0.95
     papers
    0.90
     deadlines
    0.83
     documents
    0.81
     filed
    0.81
     Papers
    0.76
     deadline
    0.72
     clerk
    0.70
     Clerk
    0.69
    BOX
    0.69
    Act Density 0.029%

    No Known Activations