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

    Neuronpedia

    INDEX
    Explanations

    variations of the root word "ra" and related terms in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teil
    -0.20
    pack
    -0.19
    cke
    -0.19
    pel
    -0.19
    tech
    -0.19
    lla
    -0.19
    tek
    -0.17
    nam
    -0.17
    vi
    -0.16
    nd
    -0.16
    POSITIVE LOGITS
    e
    0.28
    u
    0.28
    ctions
    0.27
    o
    0.26
    eer
    0.25
    iw
    0.25
    utom
    0.25
    a
    0.24
    uthor
    0.24
    ut
    0.23
    Act Density 0.097%

    No Known Activations