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

    Neuronpedia

    INDEX
    Explanations

    television program titles and associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endor
    -0.20
    asel
    -0.19
    bose
    -0.17
    маз
    -0.16
    trusted
    -0.15
    allel
    -0.15
    orest
    -0.15
    ANTE
    -0.14
    /interface
    -0.14
    rosso
    -0.14
    POSITIVE LOGITS
     Eff
    0.17
    iku
    0.16
     Davies
    0.15
     Lever
    0.15
    530
    0.15
     Attempts
    0.14
    il
    0.14
    904
    0.14
     Pierce
    0.14
    516
    0.14
    Act Density 0.034%

    No Known Activations