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

    Neuronpedia

    INDEX
    Explanations

    text related to visuals or actions being described

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shown" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entric
    -0.76
    claimer
    -0.74
    ilit
    -0.72
    idian
    -0.70
    pex
    -0.70
    ascus
    -0.69
    lly
    -0.69
    alez
    -0.69
    ignt
    -0.67
    economic
    -0.66
    POSITIVE LOGITS
    ered
    0.95
    runners
    0.90
     Thumbnails
    0.89
    ¶æ
    0.88
    rooms
    0.83
     flashes
    0.80
    Haunted
    0.79
    »
    0.74
    biz
    0.73
    otes
    0.72
    Act Density 0.046%

    No Known Activations