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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or named entities related to news stories or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ply
    -0.67
    anship
    -0.62
    length
    -0.61
     lengths
    -0.60
    Fine
    -0.60
    uning
    -0.58
    ERAL
    -0.58
    ithering
    -0.58
     sheer
    -0.58
    ade
    -0.57
    POSITIVE LOGITS
     closest
    0.86
    liest
    0.85
    iest
    0.80
     nearest
    0.78
     hardest
    0.74
     dstg
    0.73
     tallest
    0.70
     holiest
    0.69
    channelAvailability
    0.68
     strongest
    0.67
    Act Density 3.100%

    No Known Activations