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

    Neuronpedia

    INDEX
    Explanations

    references to displaying or presenting something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "show" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kson
    -0.71
    adesh
    -0.64
    ataka
    -0.63
    etary
    -0.61
     manif
    -0.60
    ades
    -0.60
    prime
    -0.60
    alez
    -0.59
     heading
    -0.59
     Blackwell
    -0.58
    POSITIVE LOGITS
    ered
    1.17
    biz
    1.04
    alter
    1.03
    case
    0.86
    cases
    0.86
     signs
    0.84
    runners
    0.83
    rooms
    0.82
    downs
    0.80
    boat
    0.79
    Act Density 0.061%

    No Known Activations