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

    Neuronpedia

    INDEX
    Explanations

    uses of the word "can" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iversit
    -0.17
     é£
    -0.16
    redients
    -0.15
    gL
    -0.15
    t
    -0.15
    лин
    -0.15
    gii
    -0.14
    uilder
    -0.14
    ITCH
    -0.14
    eldorf
    -0.14
    POSITIVE LOGITS
    opies
    0.36
    ning
    0.32
    isters
    0.31
    ny
    0.30
    ister
    0.30
    oes
    0.30
    nel
    0.30
    als
    0.28
    ker
    0.27
    tering
    0.27
    Act Density 0.016%

    No Known Activations