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

    Neuronpedia

    INDEX
    Explanations

    significant numeric values or variables in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -of
    -0.20
    оÑĦ
    -0.18
    vä
    -0.16
     N
    -0.16
     Sutton
    -0.15
    ç£
    -0.15
     Bradley
    -0.15
    of
    -0.15
    /tos
    -0.15
    vla
    -0.14
    POSITIVE LOGITS
    ais
    0.16
    ÐĶÐIJ
    0.16
    BarItem
    0.15
     Ten
    0.15
    اÙĬت
    0.15
    ëĶ
    0.15
    ì¸ł
    0.15
    çŃ
    0.15
    erais
    0.15
    board
    0.14
    Act Density 0.050%

    No Known Activations