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

    Neuronpedia

    INDEX
    Explanations

    news or articles related to scandals or controversies

    oai_token-act-pair · gpt-3.5-turbo

    references to news stories involving allegations of misconduct, particularly sexual misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ++++++++
    -0.73
     cannabin
    -0.68
    --+
    -0.67
    Excellent
    -0.66
     PARK
    -0.65
    reetings
    -0.64
     Assignment
    -0.63
    entary
    -0.61
     SERVICE
    -0.60
     Defin
    -0.60
    POSITIVE LOGITS
     controvers
    1.14
     blamed
    1.02
     accused
    0.99
     allegations
    0.97
     accusations
    0.96
     alleged
    0.96
     criticised
    0.94
     unsuccessfully
    0.91
     famously
    0.91
     scandals
    0.90
    Act Density 0.738%

    No Known Activations