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

    Neuronpedia

    INDEX
    Explanations

    opening phrases or formatting that indicates the beginning of sections or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.63
     استنادى
    -0.56
    ichè
    -0.53
    ORO
    -0.52
    她們
    -0.50
    UpInside
    -0.49
     $/
    -0.49
    $/
    -0.49
     råd
    -0.48
    lossene
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.89
     >=",
    0.86
     autorytatywna
    0.72
    featureID
    0.67
     AssertionError
    0.67
    المناصب
    0.66
    Diwedd
    0.65
    الدراسه
    0.64
    неопр
    0.61
     referrerpolicy
    0.60
    Act Density 0.027%

    No Known Activations