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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific research institutions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     evacuation
    -0.74
     checkout
    -0.66
     muff
    -0.66
     appearance
    -0.65
     shine
    -0.65
     handc
    -0.64
    ĻĤ
    -0.63
     misdem
    -0.63
     recourse
    -0.63
    ifts
    -0.61
    POSITIVE LOGITS
     Against
    0.81
     Cities
    0.78
     Of
    0.77
     Poverty
    0.77
     Policy
    0.77
     Register
    0.76
     Paper
    0.76
     Roads
    0.76
    idon
    0.76
    Point
    0.75
    Act Density 0.075%

    No Known Activations