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

    Neuronpedia

    INDEX
    Explanations

    references to inclusivity or universality in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    1
    -0.17
    off
    -0.17
    offs
    -0.17
    of
    -0.16
    rol
    -0.16
    563
    -0.15
    inality
    -0.15
    bar
    -0.15
     fast
    -0.15
     ones
    -0.15
    POSITIVE LOGITS
    rosse
    0.17
    ArgsConstructor
    0.16
    ieg
    0.16
    ahy
    0.16
    hoa
    0.15
    usive
    0.15
    ç½²
    0.15
    ahi
    0.14
    CLUDING
    0.14
    _UNS
    0.14
    Act Density 0.107%

    No Known Activations