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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptors indicating quality, uniqueness, and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loat
    -0.17
    bes
    -0.15
    ÑĢÑĸд
    -0.14
    /AP
    -0.14
    jar
    -0.13
    _IT
    -0.13
    HR
    -0.13
    dej
    -0.13
    urr
    -0.13
    awei
    -0.13
    POSITIVE LOGITS
     enough
    0.31
    ä¸Ķ
    0.28
     indeed
    0.24
    ness
    0.21
     Enough
    0.20
    ?
    0.18
     for
    0.18
    çļĦæĺ¯
    0.17
    ly
    0.17
    !
    0.17
    Act Density 0.643%

    No Known Activations