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

    Neuronpedia

    INDEX
    Explanations

    phrases related to workplace disputes and resignations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibia
    -0.58
    illing
    -0.57
     EMP
    -0.56
    ALD
    -0.55
    BIL
    -0.54
     brim
    -0.54
     Balanced
    -0.53
     Glob
    -0.52
     bene
    -0.52
     silhou
    -0.52
    POSITIVE LOGITS
    touch
    0.84
    Touch
    0.75
    ked
    0.74
    abit
    0.73
    ordinate
    0.71
    utters
    0.71
    byss
    0.71
    aughs
    0.71
    offensive
    0.70
    itialized
    0.68
    Act Density 0.045%

    No Known Activations