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

    Neuronpedia

    INDEX
    Explanations

    comparisons indicating superiority or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "more" and its comparative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.80
    atan
    -0.75
    heid
    -0.72
    etimes
    -0.72
    rosis
    -0.68
    pex
    -0.68
    æ©
    -0.67
    utions
    -0.67
    ovies
    -0.66
    OCK
    -0.66
    POSITIVE LOGITS
     than
    1.37
     efficient
    1.07
     likely
    1.02
     complicated
    1.02
     importantly
    0.96
     inclined
    0.96
     accurate
    0.93
     expensive
    0.91
     suited
    0.90
     important
    0.90
    Act Density 0.126%

    No Known Activations