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

    Neuronpedia

    INDEX
    Explanations

    references to measurements and quantification in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    klä
    -0.17
    pus
    -0.17
    견
    -0.17
    ISTS
    -0.15
    avier
    -0.15
    terra
    -0.15
    /commons
    -0.15
    iais
    -0.15
    ually
    -0.15
    ILON
    -0.15
    POSITIVE LOGITS
    ments
    0.32
    able
    0.24
     Taken
    0.24
     taken
    0.22
    mnt
    0.22
    ables
    0.21
    Taken
    0.21
    ably
    0.21
    nts
    0.20
    ment
    0.19
    Act Density 0.038%

    No Known Activations