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

    Neuronpedia

    INDEX
    Explanations

    instances where individuals are sharing personal experiences or stories

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    paio
    -1.25
    ichick
    -1.13
    ournal
    -1.00
     compr
    -0.96
    ibur
    -0.95
    anwhile
    -0.93
    trump
    -0.93
    panic
    -0.90
    =-=-=-=-=-=-=-=-
    -0.89
     desper
    -0.89
    POSITIVE LOGITS
    cro
    1.44
    hare
    1.13
    mates
    1.04
    ership
    0.95
    hou
    0.92
    places
    0.92
    itarian
    0.92
    Redd
    0.91
     needles
    0.91
    holders
    0.90
    Act Density 0.526%

    No Known Activations