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

    Neuronpedia

    INDEX
    Explanations

    names of toys or characters often associated with children

    oai_token-act-pair · gpt-3.5-turbo

    words with the suffix "-y", particularly related to names or cute descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itures
    -1.06
    isal
    -1.00
    aic
    -0.96
    inen
    -0.95
    iture
    -0.92
    irtual
    -0.91
    egal
    -0.89
    aution
    -0.88
    inem
    -0.87
    ormal
    -0.87
    POSITIVE LOGITS
     Bunny
    1.05
    Bee
    1.03
     Bear
    1.02
    bear
    1.02
     Doodle
    0.99
     Dee
    0.98
     Pie
    0.94
     Girl
    0.93
    bee
    0.92
     Pig
    0.91
    Act Density 0.159%

    No Known Activations