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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.70
     propOrder
    -0.62
     torchvision
    -0.57
     becauſe
    -0.56
     defaultstate
    -0.53
     posteriori
    -0.53
    ثيق
    -0.52
     straips
    -0.51
     osteoporosis
    -0.51
    olisian
    -0.51
    POSITIVE LOGITS
    `]
    0.80
    "}>
    0.77
    */].
    0.73
    ')):
    0.68
    @"
    0.68
    }{*}{
    0.67
    ++]=
    0.67
    */)
    0.66
    "]').
    0.65
    ]--;
    0.65
    Act Density 0.551%

    No Known Activations