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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.17
    hlen
    -0.16
    ESCO
    -0.15
    otes
    -0.15
    oise
    -0.15
    oker
    -0.15
    cks
    -0.15
    ource
    -0.15
    -es
    -0.14
    oon
    -0.14
    POSITIVE LOGITS
    ums
    0.17
    ers
    0.17
    -HT
    0.17
    ened
    0.16
    nos
    0.16
    .TestTools
    0.16
    enment
    0.15
    ening
    0.15
    ings
    0.15
    erman
    0.15
    Act Density 0.115%

    No Known Activations