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

    Neuronpedia

    INDEX
    Explanations

    phrases related to common sense

    oai_token-act-pair · gpt-3.5-turbo

    references to "common sense."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Stars
    -0.77
    chrom
    -0.72
    ISS
    -0.71
    atern
    -0.70
    raph
    -0.69
    quart
    -0.68
    ench
    -0.68
    soon
    -0.67
    âĸ¬âĸ¬
    -0.64
    seys
    -0.64
    POSITIVE LOGITS
    smanship
    0.93
     dictates
    0.77
     chops
    0.70
     decency
    0.69
     advice
    0.67
    ensical
    0.67
     scissors
    0.66
    manship
    0.66
     Reason
    0.65
     prag
    0.65
    Act Density 0.063%

    No Known Activations