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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making arguments and presenting cases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating arguments or debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chang
    -0.70
     births
    -0.64
     servicing
    -0.62
    ufact
    -0.61
    chel
    -0.59
    ghai
    -0.59
    ecast
    -0.59
     exch
    -0.59
     teased
    -0.58
     reborn
    -0.58
    POSITIVE LOGITS
     arguments
    1.35
     argument
    1.34
    argument
    1.32
     assertions
    1.31
     assertion
    1.31
     contention
    1.24
     claim
    1.23
     objections
    1.19
     objection
    1.19
    Arg
    1.19
    Act Density 1.000%

    No Known Activations