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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gand
    -0.17
     kino
    -0.16
     dial
    -0.16
     Bang
    -0.15
    arda
    -0.14
     BAM
    -0.14
     Moz
    -0.14
    Metrics
    -0.14
    uges
    -0.14
    bang
    -0.14
    POSITIVE LOGITS
    оваÑĢ
    0.18
     Slut
    0.18
    ajaran
    0.16
    _AI
    0.16
     Imports
    0.16
     Frequ
    0.16
    aker
    0.16
    ÑĥлÑİ
    0.15
    chine
    0.15
     Beverage
    0.15
    Act Density 0.001%

    No Known Activations