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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notation related to limits and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erland
    -0.18
    ppo
    -0.17
    >NN
    -0.16
    oke
    -0.16
    curity
    -0.16
    awai
    -0.15
    μβ
    -0.15
    gn
    -0.15
    Ç
    -0.14
    bject
    -0.14
    POSITIVE LOGITS
    ↵
    0.16
    ëĮĢ
    0.15
    897
    0.14
    antro
    0.14
    -ing
    0.14
    RIES
    0.14
    Cit
    0.13
    ï¸ı
    0.13
    Ìĥ
    0.13
    sl
    0.13
    Act Density 0.138%

    No Known Activations