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

    Neuronpedia

    INDEX
    Explanations

    links or mentions from social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol repeated multiple times in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apers
    -0.83
    ordinate
    -0.77
     compens
    -0.77
    ixel
    -0.75
    ignty
    -0.73
    worms
    -0.69
    amiya
    -0.66
    appropri
    -0.66
    wagen
    -0.66
    arden
    -0.66
    POSITIVE LOGITS
    ————————
    1.02
    ————
    0.90
     VIDEOS
    0.82
    ————————————————
    0.82
     Jem
    0.77
     RT
    0.75
    avanaugh
    0.74
     Rabbi
    0.73
     Ùħ
    0.72
     âĺ
    0.71
    Act Density 0.055%

    No Known Activations