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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts

    oai_token-act-pair · gpt-3.5-turbo

    closing parentheses that appear at the end of numerical or list formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Thumbnail
    -0.61
    reach
    -0.60
    enta
    -0.60
    hor
    -0.60
    role
    -0.60
    chin
    -0.59
    worldly
    -0.59
    asha
    -0.59
    icial
    -0.59
    ¬¼
    -0.58
    POSITIVE LOGITS
     Flavoring
    0.73
     namely
    0.72
     nevertheless
    0.71
     however
    0.71
     etc
    0.69
    ————————
    0.67
     whereas
    0.67
     preferring
    0.67
     meanwhile
    0.65
    775
    0.64
    Act Density 0.066%

    No Known Activations