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

    Neuronpedia

    INDEX
    Explanations

    specific purposes or functions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with purpose and context within various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Balls
    -0.63
     typo
    -0.59
    ModLoader
    -0.59
    imming
    -0.57
     Speedway
    -0.56
     Doors
    -0.56
    cknowled
    -0.55
    Bir
    -0.55
    Dro
    -0.55
     Fruit
    -0.55
    POSITIVE LOGITS
     alone
    0.83
    ativity
    0.74
     onwards
    0.73
    illet
    0.69
     prev
    0.69
     onward
    0.68
     viz
    0.67
    rongh
    0.65
    ios
    0.64
    atics
    0.64
    Act Density 0.137%

    No Known Activations