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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and regulatory language

    oai_token-act-pair · gpt-3.5-turbo

    instances of conditional statements and references to parties or entities involved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOW
    -0.63
    Rs
    -0.61
     understandably
    -0.60
    stown
    -0.60
     Loren
    -0.59
    rules
    -0.59
    onday
    -0.59
    ocracy
    -0.59
     Conrad
    -0.58
     Hoo
    -0.58
    POSITIVE LOGITS
    chard
    1.26
    ifice
    1.25
    acle
    1.22
    acles
    1.21
    nam
    1.16
    Else
    1.15
     otherwise
    1.14
    chid
    1.06
    ific
    1.03
    GAN
    1.00
    Act Density 0.143%

    No Known Activations