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

    Neuronpedia

    INDEX
    Explanations

    mentions of watching or viewing content

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pport
    -0.75
     thereof
    -0.73
    gpu
    -0.72
    thood
    -0.69
     namely
    -0.68
    onse
    -0.68
     suppose
    -0.67
    abilities
    -0.67
    iatus
    -0.66
    manship
    -0.66
    POSITIVE LOGITS
     latest
    1.22
     same
    1.16
     entire
    1.05
     hottest
    1.00
     remainder
    1.00
     following
    0.98
     earliest
    0.96
     aforementioned
    0.95
     newest
    0.93
     contents
    0.92
    Act Density 0.359%

    No Known Activations