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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software development and computer networks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bot
    -0.65
    oret
    -0.65
    ython
    -0.63
    ropolis
    -0.60
    uristic
    -0.60
    bart
    -0.59
    animate
    -0.58
    pid
    -0.57
     Koz
    -0.57
    aroo
    -0.56
    POSITIVE LOGITS
     respectively
    2.27
     alike
    1.97
    depending
    1.13
     simultaneously
    1.00
     interchange
    0.88
     depending
    0.88
    hips
    0.88
     collide
    0.87
     concurrently
    0.85
     jointly
    0.83
    Act Density 0.693%

    No Known Activations