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

    Neuronpedia

    INDEX
    Explanations

    references to various types of candy

    oai_token-act-pair · gpt-3.5-turbo

    references to candy and confectionery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NCT
    -0.69
    chron
    -0.68
     transcript
    -0.64
     transcription
    -0.63
     Chronicle
    -0.62
     Own
    -0.61
     VIEW
    -0.60
     Hutchinson
    -0.60
    Published
    -0.60
     Construct
    -0.59
    POSITIVE LOGITS
     candy
    1.26
     cane
    1.05
     sweets
    1.02
     Candy
    0.97
    mallow
    0.97
     cand
    0.90
     snacks
    0.83
     pudding
    0.83
     wra
    0.83
    fruit
    0.82
    Act Density 0.008%

    No Known Activations