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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making reports, recommendations, or announcements

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to announcements and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hated
    -0.64
     immortal
    -0.63
     cursed
    -0.62
     rejoice
    -0.62
     gore
    -0.62
     gent
    -0.62
     despise
    -0.62
     despised
    -0.61
     bast
    -0.61
     transpl
    -0.61
    POSITIVE LOGITS
     tomorrow
    1.02
     feasibility
    0.98
    Draft
    0.87
     details
    0.81
     outlining
    0.81
     specifics
    0.80
     proposals
    0.78
     recommendations
    0.77
     revise
    0.76
    iann
    0.76
    Act Density 0.464%

    No Known Activations