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

    Neuronpedia

    INDEX
    Explanations

    mentions related to organizations or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -0.64
    pire
    -0.64
     guiName
    -0.63
     Gur
    -0.59
     Guan
    -0.59
    ostic
    -0.58
     Mayweather
    -0.58
    ////
    -0.58
    furt
    -0.58
     Detected
    -0.58
    POSITIVE LOGITS
    mates
    1.76
    mate
    1.48
     mates
    1.45
     mate
    1.11
     counterparts
    0.98
     colleague
    0.92
     brethren
    0.87
    leader
    0.87
    men
    0.86
     colleagues
    0.81
    Act Density 0.200%

    No Known Activations