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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures related to programming logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allis
    -0.17
     Sud
    -0.15
     initials
    -0.15
    erland
    -0.15
    528
    -0.15
     Fel
    -0.15
    428
    -0.15
    ayo
    -0.15
    ersh
    -0.14
     Kingston
    -0.14
    POSITIVE LOGITS
     Lem
    0.16
    /Area
    0.15
    ake
    0.15
    razione
    0.14
    npos
    0.14
    .Events
    0.14
    inja
    0.14
    igham
    0.14
     leaderboard
    0.14
    akes
    0.14
    Act Density 0.442%

    No Known Activations