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

    Neuronpedia

    INDEX
    Explanations

    parentheses and brackets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Slug
    -0.72
     Ort
    -0.72
     Submit
    -0.67
     Rohingya
    -0.67
     Calculator
    -0.67
     Template
    -0.67
     Maced
    -0.66
     Mechdragon
    -0.66
     Vegan
    -0.65
     Veter
    -0.65
    POSITIVE LOGITS
    their
    1.24
    them
    1.19
    his
    1.14
    enough
    1.14
    necess
    1.12
    sic
    1.11
    him
    1.11
    been
    1.08
    appropriate
    1.08
    the
    1.08
    Act Density 1.570%

    No Known Activations