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

    Neuronpedia

    INDEX
    Explanations

    statements containing dashes in them

    oai_token-act-pair · gpt-3.5-turbo

    sections or phrases that signify a change or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.78
     chained
    -0.66
     shove
    -0.64
     extraction
    -0.64
     plaster
    -0.63
    spir
    -0.62
     drip
    -0.62
     servicing
    -0.61
     grips
    -0.61
     levers
    -0.60
    POSITIVE LOGITS
     Fever
    0.76
     Comments
    0.75
    =-=-=-=-
    0.74
    ADVERTISEMENT
    0.74
     Advertisement
    0.74
     Transcript
    0.72
     Reporter
    0.70
    Edited
    0.69
    ––
    0.69
     Ibid
    0.68
    Act Density 0.039%

    No Known Activations