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

    Neuronpedia

    INDEX
    Explanations

    words related to emotions, physical sensations, and social interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppel
    -0.65
    asketball
    -0.63
    REE
    -0.63
    wb
    -0.63
    FF
    -0.59
    ificantly
    -0.58
     Accounting
    -0.58
    LAND
    -0.58
    001
    -0.57
    iolet
    -0.56
    POSITIVE LOGITS
    iest
    1.39
     afforded
    1.03
     surrounding
    1.02
     inherent
    1.02
     emanating
    0.97
    iness
    0.92
     generated
    0.91
     aspect
    0.89
     wrought
    0.89
     plag
    0.86
    Act Density 0.563%

    No Known Activations