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

    Neuronpedia

    INDEX
    Explanations

    personal stories or anecdotes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.51
    <?
    -1.06
    /**
    -0.95
    /*
    -0.87
    ⓧ
    -0.82
    
    -0.73
    #
    -0.69
    HasColumnType
    -0.65
    HasAnnotation
    -0.65
    ngOnDestroy
    -0.63
    POSITIVE LOGITS
     maneu
    1.63
     affor
    1.54
     impra
    1.52
     increa
    1.52
     emphat
    1.49
     guarante
    1.48
     disgra
    1.48
     desir
    1.48
     effe
    1.48
     !...
    1.47
    Act Density 0.760%

    No Known Activations