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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social issues and societal structures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ob
    -0.79
    ILY
    -0.73
    kamp
    -0.71
    onis
    -0.67
    opoly
    -0.66
    OB
    -0.66
    ointment
    -0.66
    achus
    -0.65
    osate
    -0.65
    verend
    -0.63
    POSITIVE LOGITS
     pesky
    1.04
     wishing
    0.98
     who
    0.93
     kinds
    0.84
    who
    0.80
     interested
    0.79
     wanting
    0.75
     unfamiliar
    0.75
     favoring
    0.73
     fateful
    0.72
    Act Density 0.282%

    No Known Activations