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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate relationships or comparisons between concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    一体
    -0.49
    уса
    -0.47
    abord
    -0.47
    getSeconds
    -0.43
    usiai
    -0.43
     ?
    -0.42
     additional
    -0.42
     <
    -0.41
    częściej
    -0.41
     $
    -0.41
    POSITIVE LOGITS
     myſelf
    0.80
     houſe
    0.74
    ItemBackground
    0.74
     Theſe
    0.74
    ſelf
    0.73
     ſtate
    0.72
    CloseOperation
    0.71
     كومونز
    0.71
    ]--;
    0.69
     ftate
    0.68
    Act Density 0.177%

    No Known Activations