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

    Neuronpedia

    INDEX
    Explanations

    instances of structured phrases that start with "to the"

    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
    reau
    -0.68
     followed
    -0.65
     Takes
    -0.64
    eton
    -0.63
    Split
    -0.62
    leground
    -0.62
    packages
    -0.61
    .–
    -0.60
    chu
    -0.60
    esh
    -0.60
    POSITIVE LOGITS
     extent
    1.45
     detriment
    1.25
     fullest
    1.21
     tune
    1.01
    rouse
    0.99
    venge
    0.97
     same
    0.95
     nearest
    0.93
     forefront
    0.92
     depths
    0.88
    Act Density 0.260%

    No Known Activations