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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating potential consequences or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aze
    -0.19
    AZE
    -0.16
    iesta
    -0.14
     elevation
    -0.14
    vnÃŃ
    -0.14
    anca
    -0.14
    宿
    -0.14
    æ´¾
    -0.14
     Silk
    -0.13
    swire
    -0.13
    POSITIVE LOGITS
    reau
    0.17
     worse
    0.16
    Æ°a
    0.16
    unless
    0.15
    ãĥ³ãĥĩ
    0.15
     Fortunately
    0.15
     vice
    0.15
    Unless
    0.14
    egasus
    0.14
    zy
    0.14
    Act Density 0.269%

    No Known Activations