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

    Neuronpedia

    INDEX
    Explanations

    percentage values and their formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.93
     ―――――
    -0.87
     doubtnut
    -0.83
     ་་
    -0.78
     Monfieur
    -0.72
     myſelf
    -0.72
     Houſe
    -0.70
     whoſe
    -0.68
     InputDecoration
    -0.68
     itſelf
    -0.67
    POSITIVE LOGITS
     %
    1.83
    =%
    1.80
    /%
    1.63
    :%
    1.51
    (%
    1.47
     (%
    1.39
    -%
    1.38
     "%
    1.22
    _%
    1.18
    ,%
    1.13
    Act Density 0.070%

    No Known Activations