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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving equations and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĸ¹
    -0.18
    abra
    -0.16
    uja
    -0.15
     Bowling
    -0.15
    .dc
    -0.15
     Gates
    -0.15
    iaux
    -0.14
    eatures
    -0.14
    گرÛĮ
    -0.14
     unpopular
    -0.13
    POSITIVE LOGITS
    Å¡i
    0.15
    rones
    0.15
    ÙĨÙħ
    0.15
     sécur
    0.15
     Lambert
    0.14
    IRR
    0.14
    angan
    0.14
    conference
    0.14
    èĪĮ
    0.13
    ornings
    0.13
    Act Density 0.127%

    No Known Activations