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

    Neuronpedia

    INDEX
    Explanations

    mentions of achievements or awards

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     umb
    -0.79
     tempor
    -0.72
    irit
    -0.70
    arre
    -0.65
     disturbances
    -0.64
    dayName
    -0.64
     vigil
    -0.64
    rir
    -0.64
    ework
    -0.63
     interf
    -0.62
    POSITIVE LOGITS
     contender
    1.33
     finalists
    1.31
     contenders
    1.29
     winner
    1.23
    Winner
    1.22
     winners
    1.21
     nominations
    1.21
     nomination
    1.17
     rankings
    1.17
     nominees
    1.13
    Act Density 5.952%

    No Known Activations