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

    Neuronpedia

    INDEX
    Explanations

    references to different types of candy

    oai_token-act-pair · gpt-3.5-turbo

    references to candy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inen
    -0.69
    chron
    -0.65
     transcript
    -0.64
     Shap
    -0.64
     Hutchinson
    -0.63
    ebin
    -0.63
    lihood
    -0.62
     Socialist
    -0.62
     advers
    -0.62
     NCT
    -0.61
    POSITIVE LOGITS
     cane
    1.13
     candy
    1.06
    mallow
    0.98
    strip
    0.89
     wra
    0.88
    bucks
    0.86
    flake
    0.85
    fruit
    0.84
    corn
    0.83
     daddy
    0.83
    Act Density 0.013%

    No Known Activations