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

    Neuronpedia

    INDEX
    Explanations

    proper names or places containing diacritics or symbols

    oai_token-act-pair · gpt-3.5-turbo

    specific terms and keywords related to ratings and reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bearer
    -0.65
     millenn
    -0.64
     conclud
    -0.62
    ĸļ
    -0.62
     suspic
    -0.61
     helicop
    -0.59
     cryst
    -0.59
     unequ
    -0.58
     prototyp
    -0.58
     academ
    -0.58
    POSITIVE LOGITS
    icz
    0.91
    ai
    0.84
    phia
    0.84
    opsis
    0.83
    nir
    0.79
    ka
    0.77
    quez
    0.77
    idae
    0.77
    ou
    0.75
    ia
    0.75
    Act Density 0.333%

    No Known Activations