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

    Neuronpedia

    INDEX
    Explanations

    specific formatting and syntax elements related to programming or code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Houſe
    -1.02
     Efq
    -0.97
    ſelf
    -0.93
     ―――――
    -0.92
     ſeveral
    -0.91
     Reſ
    -0.91
     Diſ
    -0.90
     myſelf
    -0.89
     Theſe
    -0.88
    Datuak
    -0.88
    POSITIVE LOGITS
    ,
    0.64
    .
    0.62
     far
    0.61
     
    0.58
     (
    0.56
     Far
    0.53
    ↵
    0.52
     ly
    0.50
     py
    0.49
    mente
    0.49
    Act Density 0.026%

    No Known Activations