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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons and measurements of similarity or equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     */}
    -0.60
     kec
    -0.56
    RegressionTest
    -0.55
    又是
    -0.53
    */}
    -0.51
    CopyWith
    -0.51
    "},
    -0.51
    __":
    -0.50
    __':
    -0.50
    =");
    -0.49
    POSITIVE LOGITS
     myſelf
    0.83
     poffible
    0.76
    tidaknya
    0.69
     Efq
    0.67
     rêves
    0.66
    RectangleBorder
    0.66
     travailleurs
    0.66
     acoper
    0.64
     désol
    0.64
     himſelf
    0.63
    Act Density 0.132%

    No Known Activations