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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of ambiguity or complexity in processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     and
    -0.57
     A
    -0.57
     I
    -0.54
     а
    -0.46
     “
    -0.46
     off
    -0.46
     AND
    -0.45
     a
    -0.44
     dessus
    -0.43
    :
    -0.43
    POSITIVE LOGITS
     StringTokenizer
    0.94
     theſe
    0.84
     Theſe
    0.83
     Anſ
    0.82
    تقاوى
    0.81
     Efq
    0.79
    ContentAsync
    0.79
     Shakspeare
    0.78
     Monfieur
    0.78
     iſt
    0.76
    Act Density 0.049%

    No Known Activations