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

    Neuronpedia

    INDEX
    Explanations

    terms related to actions and their variations, particularly focusing on word forms containing "act."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indre
    -0.18
    lad
    -0.15
    rieg
    -0.15
    istic
    -0.15
    á»Ĺ
    -0.15
    ald
    -0.14
    Unmount
    -0.14
    ieten
    -0.14
    ενο
    -0.14
    uler
    -0.14
    POSITIVE LOGITS
    e
    0.28
    ech
    0.25
    ei
    0.23
    uring
    0.22
    ea
    0.21
    eon
    0.21
    o
    0.20
    eur
    0.20
    eq
    0.20
    eam
    0.20
    Act Density 0.067%

    No Known Activations