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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    text or phrases that suggest a threatening or negative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Berm
    -0.56
     Nicarag
    -0.55
     Meter
    -0.54
     Olympia
    -0.53
     Wilmington
    -0.51
     Pegasus
    -0.49
     rival
    -0.48
     Valhalla
    -0.48
     Western
    -0.48
     Pan
    -0.48
    POSITIVE LOGITS
    ï¸ı
    1.44
    then
    1.00
    âĢ
    0.94
    why
    0.91
     thats
    0.85
    ðŁ
    0.85
    #
    0.83
    ðŁĺ
    0.83
    please
    0.83
    ï¸
    0.81
    Act Density 0.308%

    No Known Activations