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

    Neuronpedia

    INDEX
    Explanations

    references to the word 'tre' or 'Tre'

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    66666666
    -0.74
    ulate
    -0.70
    bleacher
    -0.70
    OK
    -0.69
    urate
    -0.67
    200000
    -0.67
    OWS
    -0.67
    abad
    -0.65
    666
    -0.62
    ulating
    -0.61
    POSITIVE LOGITS
    Tre
    1.19
    asury
    1.15
    ngth
    1.06
    asure
    1.04
    tre
    0.88
    llor
    0.85
    chy
    0.78
     tre
    0.75
    TRY
    0.73
     glim
    0.72
    Act Density 0.009%

    No Known Activations