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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms related to coding, development, and problem-solving

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reconstruction
    -0.62
    thodox
    -0.61
     Annex
    -0.59
     Bak
    -0.59
    ilts
    -0.58
    legal
    -0.54
    endiary
    -0.54
    hawks
    -0.54
    Il
    -0.53
    Bridge
    -0.53
    POSITIVE LOGITS
     yourself
    1.59
     yourselves
    1.38
     Yourself
    1.11
     your
    0.94
     YOUR
    0.89
    your
    0.79
    Your
    0.74
     oneself
    0.69
     Your
    0.68
     wasting
    0.65
    Act Density 0.602%

    No Known Activations