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

    Neuronpedia

    INDEX
    Explanations

    terms related to additional costs or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chow
    -0.15
     Watt
    -0.14
    oton
    -0.14
     ÑģпоÑĢ
    -0.14
    endors
    -0.14
    anggan
    -0.14
    cko
    -0.14
    authenticated
    -0.13
    ×¢
    -0.13
     xuyên
    -0.13
    POSITIVE LOGITS
    ordin
    0.21
    ordinary
    0.19
    endum
    0.19
    /new
    0.17
    ord
    0.17
    -extra
    0.16
    CTION
    0.16
    tti
    0.16
    ORD
    0.16
    halb
    0.16
    Act Density 0.048%

    No Known Activations