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

    Neuronpedia

    INDEX
    Explanations

    numbers relating to specific age groups

    oai_token-act-pair · gpt-3.5-turbo

    references to specific age ranges and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cac
    -0.60
     redund
    -0.58
     fug
    -0.58
     Cheong
    -0.58
     ingred
    -0.57
     envoy
    -0.57
     capacitor
    -0.57
     enh
    -0.57
     POL
    -0.56
     jams
    -0.56
    POSITIVE LOGITS
    +.
    1.20
    +,
    1.18
    +)
    1.09
    yrs
    0.95
     onwards
    0.91
     onward
    0.87
    ½
    0.87
    digy
    0.80
    Age
    0.80
    Kids
    0.78
    Act Density 0.077%

    No Known Activations