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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating personal experiences or reflections on life events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortex
    -0.82
    DOS
    -0.71
    de
    -0.69
     Telecommunications
    -0.69
    ilt
    -0.67
    igon
    -0.67
    ardless
    -0.65
    shock
    -0.62
    mast
    -0.62
    analysis
    -0.61
    POSITIVE LOGITS
     else
    1.41
    Else
    1.25
     akin
    0.94
     unheard
    0.93
     Else
    0.87
     shameful
    0.83
     intangible
    0.82
     unusual
    0.81
     unimaginable
    0.80
     resembling
    0.78
    Act Density 0.030%

    No Known Activations