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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sign."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undry
    -1.64
    ")]
    -1.59
     thee
    -1.54
    '))
    -1.51
    laid
    -1.50
    '));
    -1.50
    '>
    -1.49
    rian
    -1.43
    "));
    -1.43
    AndroidRuntime
    -1.40
    POSITIVE LOGITS
    ĩ
    2.00
    ored
    1.89
    ificantly
    1.87
    orable
    1.86
    ĻĤ
    1.72
    bugs
    1.63
     submissions
    1.56
    stones
    1.46
    orest
    1.46
    rams
    1.45
    Act Density 0.903%

    No Known Activations