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

    Neuronpedia

    INDEX
    Explanations

    ratings and reviews, particularly five-star evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /stretch
    -0.15
    zh
    -0.14
    ongan
    -0.14
    shint
    -0.14
    egov
    -0.14
    olumn
    -0.14
    aj
    -0.13
     stabilize
    -0.13
    ÃŃny
    -0.13
    tru
    -0.13
    POSITIVE LOGITS
     star
    0.73
     stars
    0.65
    -star
    0.63
    star
    0.61
     Star
    0.59
    _star
    0.55
    Star
    0.54
    .star
    0.52
     Stars
    0.52
    stars
    0.52
    Act Density 0.137%

    No Known Activations