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

    Neuronpedia

    INDEX
    Explanations

    positive qualities or characteristics related to an individual

    oai_token-act-pair · gpt-3.5-turbo

    qualities and attributes that contribute to a person's character and popularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Situation
    -0.74
    akh
    -0.67
     COP
    -0.64
     inaction
    -0.64
     Timeline
    -0.63
    Activity
    -0.63
     Procedure
    -0.63
    /?
    -0.62
    odynamic
    -0.61
     Procedures
    -0.61
    POSITIVE LOGITS
     matched
    1.04
     outwe
    1.01
     unmatched
    1.00
     contrasted
    0.99
     outweigh
    0.97
     overshadow
    0.94
     shone
    0.94
     contagious
    0.93
     compliment
    0.93
     translate
    0.91
    Act Density 0.384%

    No Known Activations