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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming and data input/output operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /is
    -0.18
    infeld
    -0.16
    inea
    -0.15
    Insensitive
    -0.15
    abeth
    -0.14
    kup
    -0.14
    egg
    -0.14
    haf
    -0.14
    avic
    -0.14
     Ñģобой
    -0.14
    POSITIVE LOGITS
    /output
    0.47
    -output
    0.42
    ted
    0.40
    ting
    0.38
    ters
    0.32
    TING
    0.28
    MethodManager
    0.24
    /out
    0.21
    tings
    0.21
    ten
    0.20
    Act Density 0.019%

    No Known Activations