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

    Neuronpedia

    INDEX
    Explanations

    references to specific movie titles or TV show names

    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
    strap
    -0.86
     complying
    -0.75
    âĢij
    -0.74
     owing
    -0.72
     because
    -0.72
     without
    -0.71
    fax
    -0.70
     fuelled
    -0.69
    Iterator
    -0.67
     countered
    -0.67
    POSITIVE LOGITS
     latter
    1.15
     aforementioned
    1.15
     same
    1.10
     infamous
    1.03
     coolest
    0.97
     proverbial
    0.96
     latest
    0.96
     hottest
    0.95
     entirety
    0.94
     dreaded
    0.93
    Act Density 1.177%

    No Known Activations