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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to politics and media personalities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.90
    onyms
    -0.89
    ħĭ
    -0.80
    insula
    -0.79
    vertisement
    -0.77
    ulhu
    -0.75
    illing
    -0.73
    lucent
    -0.73
    achusetts
    -0.73
    ensing
    -0.73
    POSITIVE LOGITS
     Fallon
    0.99
     capped
    0.69
     Spicer
    0.69
     Mane
    0.68
    Fall
    0.68
     Yard
    0.66
     Spiegel
    0.66
     Manning
    0.65
     HM
    0.65
     Kimmel
    0.65
    Act Density 0.045%

    No Known Activations