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

    Neuronpedia

    INDEX
    Explanations

    terminology related to scientific research and experimentation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to scientific methods and principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hirt
    -0.74
    ammy
    -0.70
    ync
    -0.64
     Liv
    -0.63
     TOTAL
    -0.61
     Jury
    -0.60
    ollar
    -0.60
    creen
    -0.60
     Oprah
    -0.59
     Citiz
    -0.58
    POSITIVE LOGITS
    lessly
    1.09
    lessness
    1.03
    fulness
    1.02
    making
    0.95
    abl
    0.91
    ably
    0.89
    makers
    0.87
    fully
    0.86
    uality
    0.85
    ful
    0.84
    Act Density 0.423%

    No Known Activations