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

    Neuronpedia

    INDEX
    Explanations

    assertions or claims about truth and certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.47
    <?
    -0.85
    
    -0.83
    <?
    -0.82
    /***
    -0.81
    ⓧ
    -0.80
     disbur
    -0.73
     defray
    -0.70
     assiste
    -0.66
     endow
    -0.65
    POSITIVE LOGITS
     pylab
    0.83
    číta
    0.78
     heapq
    0.68
    jectures
    0.68
    :]:
    0.67
    cristo
    0.66
     ados
    0.65
    irvana
    0.65
     functools
    0.65
     pymysql
    0.64
    Act Density 0.655%

    No Known Activations