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

    Neuronpedia

    INDEX
    Explanations

    quantities and measurements related to performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tti
    -0.16
    uft
    -0.15
    astle
    -0.15
    reon
    -0.14
    butt
    -0.14
    าม
    -0.13
    lein
    -0.13
    /interfaces
    -0.13
    /layouts
    -0.13
     ÑıкоÑģÑĤÑĸ
    -0.13
    POSITIVE LOGITS
     around
    0.18
    0.16
     just
    0.16
    infinity
    0.16
    lan
    0.15
    135
    0.15
    innen
    0.15
     tent
    0.14
     minus
    0.14
     cel
    0.14
    Act Density 0.178%

    No Known Activations