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

    Neuronpedia

    INDEX
    Explanations

    terms related to permits, fines, and official documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ribbon
    -0.16
    enek
    -0.15
    irit
    -0.15
    _BUSY
    -0.15
     Maul
    -0.14
    zcze
    -0.14
    æĭ³
    -0.14
     Noel
    -0.14
    enko
    -0.14
    idor
    -0.14
    POSITIVE LOGITS
    (s
    0.23
    _DM
    0.15
     Vern
    0.15
    ahun
    0.15
    (es
    0.15
    prav
    0.14
    ietf
    0.14
    ãĥ©ãĤ¹
    0.14
    ckill
    0.14
    strup
    0.14
    Act Density 0.215%

    No Known Activations