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

    Neuronpedia

    INDEX
    Explanations

    items of critique or controversy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    worldly
    -0.72
    ,
    -0.68
    ome
    -0.66
    ":"/
    -0.66
    ally
    -0.65
    agine
    -0.62
    sth
    -0.61
    entimes
    -0.60
    ocry
    -0.58
    azing
    -0.57
    POSITIVE LOGITS
     etc
    0.93
     LLC
    0.90
     huh
    0.86
     aka
    0.85
     Inc
    0.81
     supra
    0.80
     ISBN
    0.76
    000
    0.75
     Calif
    0.73
     which
    0.73
    Act Density 2.777%

    No Known Activations