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

    Neuronpedia

    INDEX
    Explanations

    the name "Rodrick" with different variations in text surrounding it

    oai_token-act-pair · gpt-3.5-turbo

    the name "Rod" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     secured
    -0.75
     securing
    -0.69
     starters
    -0.67
     secure
    -0.64
     lifts
    -0.63
     verification
    -0.62
     fully
    -0.61
     shelters
    -0.59
     TOR
    -0.59
     mit
    -0.58
    POSITIVE LOGITS
    odd
    4.60
    ods
    1.48
     Odd
    1.20
    oddy
    1.17
    odder
    1.17
    unn
    1.08
    OD
    1.04
     odd
    1.03
    od
    1.02
    rawn
    1.02
    Act Density 0.011%

    No Known Activations