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

    Neuronpedia

    INDEX
    Explanations

    backticks and other special characters used for code notation or syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Elias
    -0.16
    istrovstvÃŃ
    -0.15
    ToLeft
    -0.15
    Âłmph
    -0.14
    loit
    -0.14
    ãĥ©ãĤ¹
    -0.14
    ův
    -0.14
    _nested
    -0.14
    omanip
    -0.14
    alem
    -0.14
    POSITIVE LOGITS
    ely
    0.15
    venues
    0.14
    angu
    0.14
    ply
    0.14
    abe
    0.14
    attern
    0.14
    Ñī
    0.14
    ryan
    0.13
     Dut
    0.13
     damage
    0.13
    Act Density 0.012%

    No Known Activations