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

    Neuronpedia

    INDEX
    Explanations

    references to inclusivity or completeness in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illes
    -0.16
    دÙĬØ«
    -0.15
     Dir
    -0.14
    ior
    -0.14
    aku
    -0.14
    enberg
    -0.14
    dorf
    -0.13
    तर
    -0.13
     Farr
    -0.13
    ENTE
    -0.13
    POSITIVE LOGITS
    xCD
    0.18
     equally
    0.18
    uni
    0.16
    erty
    0.14
    oly
    0.14
    liers
    0.14
    миÑĤ
    0.14
    lex
    0.14
    lic
    0.14
    mayan
    0.14
    Act Density 0.249%

    No Known Activations