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

    Neuronpedia

    INDEX
    Explanations

    references to diversity and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ister
    -0.18
    isphere
    -0.16
    ote
    -0.15
    esda
    -0.15
    ffe
    -0.14
    iliz
    -0.14
    sets
    -0.14
    orney
    -0.14
    ilde
    -0.14
    na
    -0.14
    POSITIVE LOGITS
    /div
    0.15
     enough
    0.15
     talents
    0.15
    ERRU
    0.15
    /random
    0.14
    å§ĵ
    0.14
    ,...↵↵
    0.14
    yum
    0.14
    944
    0.13
    ErrMsg
    0.13
    Act Density 0.023%

    No Known Activations