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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating classifications or categories in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertino
    -0.16
    azon
    -0.15
    -Le
    -0.15
    unos
    -0.14
    rana
    -0.14
     Trit
    -0.14
     Lazar
    -0.14
    .mx
    -0.14
    roke
    -0.14
    gewater
    -0.14
    POSITIVE LOGITS
     perd
    0.16
    ÑĭÑģ
    0.16
    chi
    0.15
     xlink
    0.15
    iel
    0.15
    ani
    0.15
     Huck
    0.15
    tractor
    0.14
    ucz
    0.14
    ariant
    0.13
    Act Density 0.024%

    No Known Activations