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

    Neuronpedia

    INDEX
    Explanations

    information or details that help to clarify or uncover something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to revealing information or insights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heid
    -0.77
    DragonMagazine
    -0.71
    ãĥĦ
    -0.63
    ICO
    -0.63
    managed
    -0.63
    teness
    -0.63
    netflix
    -0.63
    icians
    -0.62
    ournals
    -0.61
    War
    -0.60
    POSITIVE LOGITS
     jaws
    0.85
    iencies
    0.83
    brid
    0.82
    pload
    0.77
    irts
    0.77
     hairs
    0.76
    ritten
    0.76
    itten
    0.76
    ibilities
    0.74
    inished
    0.73
    Act Density 0.021%

    No Known Activations