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

    Neuronpedia

    INDEX
    Explanations

    topics related to transportation, restaurant investigation, sports, and public service

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dialogue
    -0.77
    selves
    -0.69
     DPR
    -0.68
     Curiosity
    -0.65
     Gleaming
    -0.65
    AAAAAAAA
    -0.65
    natureconservancy
    -0.64
     Helpful
    -0.64
    ï¸
    -0.64
     Subtle
    -0.63
    POSITIVE LOGITS
     locker
    0.76
    -
    0.74
    âĢij
    0.72
    tech
    0.71
     card
    0.70
     boarding
    0.69
    -,
    0.68
     division
    0.68
    books
    0.67
    jet
    0.67
    Act Density 4.134%

    No Known Activations