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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions indicating uncertainty or lack of understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recently
    -0.51
     ovan
    -0.49
    infeld
    -0.47
     Play
    -0.45
     Die
    -0.45
    dede
    -0.44
    <eos>
    -0.44
    uol
    -0.44
    angular
    -0.43
     geng
    -0.43
    POSITIVE LOGITS
     ModelExpression
    0.93
     autorytatywna
    0.86
    yntaxException
    0.85
    Portail
    0.83
     cdti
    0.81
    endforeach
    0.76
    ForRow
    0.76
    __':
    0.76
    __":
    0.76
    SuccessListener
    0.75
    Act Density 0.147%

    No Known Activations