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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and code snippets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    quer
    -0.75
    hell
    -0.74
    ravel
    -0.73
    ãĥĥãĥī
    -0.66
    iov
    -0.66
    onz
    -0.65
    ctions
    -0.63
    venge
    -0.63
    ibur
    -0.63
    ikuman
    -0.63
    POSITIVE LOGITS
    ably
    0.99
     how
    0.97
     discrepancies
    0.83
     inconsistencies
    0.81
     similarities
    0.75
    flies
    0.72
    uality
    0.71
     flaws
    0.69
    pad
    0.67
     Powell
    0.66
    Act Density 0.739%

    No Known Activations