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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating confirmation or announcement of actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    statements related to employment status changes and official communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toggle
    -0.80
    Enlarge
    -0.77
     Wonders
    -0.76
     underdog
    -0.71
     empires
    -0.69
     someday
    -0.69
    overty
    -0.69
     dystop
    -0.69
     utopian
    -0.68
     Economist
    -0.66
    POSITIVE LOGITS
    sic
    1.05
     Plaintiff
    1.03
    %"
    1.00
     âĢ¦"
    0.98
     Defendant
    0.97
     ..."
    0.97
    )",
    0.95
    âĢ¦"
    0.94
    ),"
    0.93
     enqu
    0.93
    Act Density 1.148%

    No Known Activations