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

    Neuronpedia

    INDEX
    Explanations

    legal and regulatory terms and discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.65
    retty
    -0.64
    udos
    -0.57
     anecd
    -0.56
    enegger
    -0.55
    fortunately
    -0.55
    anwhile
    -0.54
    herer
    -0.54
    jri
    -0.52
    eday
    -0.52
    POSITIVE LOGITS
    oplan
    0.56
     Allaah
    0.55
    ¶
    0.55
    ratom
    0.55
     Belfast
    0.51
     Cannabis
    0.50
     Rohingya
    0.50
     Xperia
    0.49
    \":
    0.48
     cannabis
    0.48
    Act Density 6.039%

    No Known Activations