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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to engineering and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahlen
    -0.15
    acher
    -0.15
     ÙħØ«
    -0.14
    aben
    -0.14
    ürn
    -0.14
    yr
    -0.14
    arda
    -0.14
     Abr
    -0.14
    ekl
    -0.14
    ais
    -0.13
    POSITIVE LOGITS
     which
    0.16
    mage
    0.14
     kå
    0.14
    SError
    0.14
    osexual
    0.14
    esses
    0.14
    itude
    0.14
    ominator
    0.13
    SGlobal
    0.13
    Ìĥ
    0.13
    Act Density 0.222%

    No Known Activations