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

    Neuronpedia

    INDEX
    Explanations

    variations of the letter 'd' and its presence in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ksam
    -0.16
    constructor
    -0.15
    ncia
    -0.14
    ederation
    -0.14
    heritance
    -0.14
    ç²¾
    -0.14
    HITE
    -0.14
    asin
    -0.14
    nts
    -0.14
    ERGE
    -0.14
    POSITIVE LOGITS
    ug
    0.28
    era
    0.26
    rove
    0.26
    rew
    0.26
    abb
    0.25
    rank
    0.24
    rawn
    0.24
    one
    0.23
    oubted
    0.21
    rap
    0.21
    Act Density 0.014%

    No Known Activations