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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a higher quantity or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.81
    arote
    -0.72
     BoxDecoration
    -0.72
    BoxShadow
    -0.69
    Bae
    -0.68
    principalTable
    -0.66
    jsii
    -0.65
    alb
    -0.65
    RectangleBorder
    -0.65
    !".
    -0.64
    POSITIVE LOGITS
     greater
    1.63
    Greater
    1.60
     Greater
    1.58
    greater
    1.57
    GREATER
    1.38
    greatest
    0.95
     Lesser
    0.93
     greatest
    0.92
    Greatest
    0.90
     Greatest
    0.86
    Act Density 0.099%

    No Known Activations