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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a broad range of topics or issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Walls
    -0.74
    MIT
    -0.73
     Row
    -0.69
    mit
    -0.68
     Cust
    -0.64
     Steal
    -0.63
    Hub
    -0.61
    $$$$
    -0.61
     bye
    -0.61
    ©¶æ
    -0.60
    POSITIVE LOGITS
     ranging
    0.88
     ranges
    0.78
     of
    0.78
     imaginable
    0.77
    ranging
    0.76
    range
    0.75
    ortment
    0.74
     distributions
    0.72
    finder
    0.70
    efully
    0.70
    Act Density 0.035%

    No Known Activations