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

    Neuronpedia

    INDEX
    Explanations

    references to names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ̣
    -0.15
    elsen
    -0.15
     wrench
    -0.14
     Dial
    -0.14
    rat
    -0.14
     betray
    -0.13
    EDI
    -0.13
     Bour
    -0.13
    onta
    -0.13
    as
    -0.13
    POSITIVE LOGITS
    èĥŀ
    0.17
    idth
    0.17
    ãĤħ
    0.16
    aled
    0.15
    idue
    0.15
    ısından
    0.15
    .requireNonNull
    0.15
    eree
    0.14
    OrNil
    0.14
    Falsy
    0.14
    Act Density 0.144%

    No Known Activations