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

    Neuronpedia

    INDEX
    Explanations

    words indicating temporal relationships and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asca
    -0.16
    erde
    -0.15
     Ly
    -0.15
    ahkan
    -0.15
    unn
    -0.15
     Pant
    -0.15
    пÑĢиклад
    -0.15
    Ly
    -0.15
    okrat
    -0.14
     Walton
    -0.14
    POSITIVE LOGITS
    oba
    0.17
    ujet
    0.16
    ushman
    0.15
     Somerset
    0.15
    inde
    0.15
    ighton
    0.14
     spol
    0.14
    usu
    0.14
    ighting
    0.14
    oby
    0.14
    Act Density 0.043%

    No Known Activations