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

    Neuronpedia

    INDEX
    Explanations

    mentions of news anchors or commentators

    oai_token-act-pair · gpt-3.5-turbo

    references to media personalities and news anchors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Corsair
    -0.69
    activation
    -0.67
    ogun
    -0.66
    TOR
    -0.65
    ahime
    -0.64
     Agric
    -0.64
    density
    -0.63
     1918
    -0.61
    venture
    -0.61
    depend
    -0.61
    POSITIVE LOGITS
     aired
    1.09
     Hannity
    1.08
     interviewer
    1.00
     Tonight
    0.98
    gyn
    0.95
     airing
    0.93
    CNN
    0.91
     anchor
    0.91
     broadcasts
    0.88
     listeners
    0.88
    Act Density 0.101%

    No Known Activations