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

    Neuronpedia

    INDEX
    Explanations

    information related to technical aspects of video games, hardware specifications, and online forums

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     proactive
    -0.76
     unders
    -0.76
     pooled
    -0.68
     cradle
    -0.67
     posture
    -0.66
     intended
    -0.65
     employment
    -0.65
     worker
    -0.65
     butcher
    -0.65
     behavioral
    -0.65
    POSITIVE LOGITS
    00
    1.23
    sbm
    1.02
    0
    1.01
    5
    1.00
     Additionally
    0.99
     Also
    0.95
    02
    0.94
    000
    0.93
    50
    0.93
     However
    0.93
    Act Density 0.151%

    No Known Activations