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

    Neuronpedia

    INDEX
    Explanations

    words related to informational content or reports, specifically in a structured format with line breaks and markers like "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    moments of high emotional intensity or pivotal plot revelations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withdrawal
    -0.72
     welding
    -0.71
     withdraw
    -0.70
    illance
    -0.70
     probation
    -0.68
     union
    -0.67
     protection
    -0.67
     exchanging
    -0.66
     shelling
    -0.66
    ewitness
    -0.65
    POSITIVE LOGITS
    Advertisement
    1.24
    Favorite
    1.10
    Anyway
    1.10
    Speaking
    1.01
    Newsletter
    1.00
    SPONSORED
    0.97
    advertisement
    0.91
    Mesh
    0.90
    Elsewhere
    0.90
    Related
    0.90
    Act Density 0.433%

    No Known Activations