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

    Neuronpedia

    INDEX
    Explanations

    terms related to competition and winning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eron
    -0.19
    lew
    -0.18
    eb
    -0.17
    ersen
    -0.16
    wine
    -0.15
    illon
    -0.15
    cki
    -0.15
    ASON
    -0.15
    iagnostics
    -0.15
    igli
    -0.14
    POSITIVE LOGITS
    nable
    0.27
    -win
    0.20
     streak
    0.19
    emaker
    0.18
    ograd
    0.18
    -loss
    0.18
    /win
    0.18
    NER
    0.18
     одеÑĢж
    0.17
    oren
    0.16
    Act Density 0.039%

    No Known Activations