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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strand
    -0.17
     posing
    -0.16
    leen
    -0.15
    ini
    -0.15
     Ãĸn
    -0.15
    hee
    -0.14
    ereg
    -0.14
     Traffic
    -0.14
    ymi
    -0.14
    icy
    -0.14
    POSITIVE LOGITS
    something
    0.18
    adiator
    0.17
    Something
    0.17
    ãy
    0.17
     Something
    0.16
     something
    0.16
    istar
    0.15
    geh
    0.15
    .Abstract
    0.14
    chedule
    0.14
    Act Density 0.200%

    No Known Activations