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

    Neuronpedia

    INDEX
    Explanations

    terms related to performance metrics and evaluations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zend
    -0.18
    late
    -0.16
    prite
    -0.15
     clave
    -0.15
    rawn
    -0.14
    åħ¶ä¸Ń
    -0.14
    erten
    -0.14
    æŃ©
    -0.14
     keys
    -0.14
    ome
    -0.14
    POSITIVE LOGITS
    па
    0.16
     fac
    0.16
    -lfs
    0.15
    ACKET
    0.14
    .getSelection
    0.14
    XB
    0.14
    ellen
    0.14
    758
    0.14
    809
    0.13
     å¾®
    0.13
    Act Density 0.019%

    No Known Activations