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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "register" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ittings
    -0.16
    lest
    -0.15
    fx
    -0.15
    lesh
    -0.15
    cek
    -0.14
    chet
    -0.14
    annes
    -0.14
    ether
    -0.14
    /meta
    -0.13
    ahren
    -0.13
    POSITIVE LOGITS
    ofi
    0.14
    enen
    0.14
    _globals
    0.14
     ÙħØ°
    0.14
    ional
    0.14
    =#
    0.14
    hus
    0.14
    horn
    0.14
    æĪ·
    0.13
    дам
    0.13
    Act Density 0.018%

    No Known Activations