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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uniqueness or prominence within categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abis
    -0.15
    enaire
    -0.14
    bij
    -0.14
    ÏĦικα
    -0.14
    rang
    -0.14
    Ø£ÙĨ
    -0.14
     environ
    -0.14
     ydk
    -0.13
    reon
    -0.13
    ä¸ĢæŃ¥
    -0.13
    POSITIVE LOGITS
    689
    0.17
    ë¡Ģ
    0.15
    atrice
    0.15
    arda
    0.14
     group
    0.14
    jo
    0.14
     Stre
    0.14
    -to
    0.14
     Brunswick
    0.14
     Knot
    0.14
    Act Density 0.110%

    No Known Activations