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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating location and direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĮ
    -0.19
    Ь
    -0.15
    itch
    -0.15
    inges
    -0.14
    igner
    -0.14
     depths
    -0.14
    олод
    -0.13
    ingle
    -0.13
    t
    -0.13
     Lifetime
    -0.13
    POSITIVE LOGITS
    /down
    0.22
    psc
    0.17
    illery
    0.17
    PCS
    0.16
    graf
    0.16
    ensburg
    0.15
     Ñģел
    0.15
    ussen
    0.15
    vetica
    0.14
    ToDate
    0.14
    Act Density 0.045%

    No Known Activations