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

    Neuronpedia

    INDEX
    Explanations

    names related to news commentators

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly Tucker Carlson

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atics
    -0.89
    atically
    -0.82
    binding
    -0.82
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.81
    mable
    -0.81
    ritis
    -0.80
    ãĤ£
    -0.77
    worldly
    -0.75
    orically
    -0.75
    spring
    -0.72
    POSITIVE LOGITS
     Carlson
    1.23
     Tucker
    1.01
    onom
    0.73
     Barney
    0.70
     Griff
    0.70
     Ellison
    0.67
    lla
    0.67
     Nunes
    0.66
     inver
    0.66
     Vald
    0.65
    Act Density 0.017%

    No Known Activations