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

    Neuronpedia

    INDEX
    Explanations

    statements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    instances and variations of the word "statement."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iencies
    -0.73
    elsius
    -0.72
    cffff
    -0.72
    MpServer
    -0.70
    rys
    -0.70
    erenn
    -0.67
    rowd
    -0.66
    ickets
    -0.66
    rentice
    -0.65
    flix
    -0.64
    POSITIVE LOGITS
     condemning
    1.09
     regarding
    1.06
     denouncing
    1.03
     uttered
    0.98
     announcing
    0.96
     attributed
    0.96
     statements
    0.95
     praising
    0.94
     Regarding
    0.93
     issued
    0.92
    Act Density 0.057%

    No Known Activations