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

    Neuronpedia

    INDEX
    Explanations

    academic references and citations related to mathematical equations and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ordered
    -0.16
     propositions
    -0.15
    obble
    -0.14
    .roll
    -0.14
    ogle
    -0.14
     Freeman
    -0.14
     Stevens
    -0.14
    ollar
    -0.13
     Kend
    -0.13
     γαÏģα
    -0.13
    POSITIVE LOGITS
    veau
    0.16
     dif
    0.16
    ataires
    0.15
    htar
    0.15
    IMS
    0.15
    ilha
    0.15
    raith
    0.14
     ÑģÑĤоÑı
    0.14
    ETYPE
    0.14
     Boundary
    0.14
    Act Density 0.913%

    No Known Activations