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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to value or significance in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    รà¸ĵ
    -0.15
    ordinate
    -0.15
    ungi
    -0.15
    comings
    -0.15
    atura
    -0.15
    celik
    -0.14
    olia
    -0.14
     whom
    -0.14
     poil
    -0.14
     Zahl
    -0.14
    POSITIVE LOGITS
    alat
    0.15
    illard
    0.15
    erd
    0.14
    ÐĶÐIJ
    0.14
    alo
    0.14
    ulis
    0.14
    assen
    0.14
    bil
    0.14
    اÙĩا
    0.14
    lossen
    0.14
    Act Density 0.000%

    No Known Activations