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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate distance or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.84
    endphp
    -0.79
    zez
    -0.73
    __':
    -0.70
    GoogleApiClient
    -0.70
    UpInside
    -0.70
    SocketChannel
    -0.68
    PositiveButton
    -0.67
    Външни
    -0.67
    PageIndex
    -0.65
    POSITIVE LOGITS
    away
    0.63
     from
    0.59
    NameInMap
    0.56
     entière
    0.49
     arric
    0.47
     away
    0.45
    Away
    0.45
    from
    0.42
     оригіналу
    0.42
    aways
    0.42
    Act Density 0.145%

    No Known Activations