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

    Neuronpedia

    INDEX
    Explanations

    words related to metaphors and abstract concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to academic concepts, particularly those related to "aphorisms" or concise statements expressing general truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PUT
    -0.88
    nings
    -0.81
    swick
    -0.80
    âĸ¬âĸ¬
    -0.78
    eer
    -0.69
     Bauer
    -0.65
     Adidas
    -0.65
    eers
    -0.65
     Clown
    -0.65
    LOAD
    -0.64
    POSITIVE LOGITS
    ysics
    1.27
    ysical
    1.24
    obia
    1.20
    orically
    1.11
    osate
    1.05
    obic
    1.05
    urst
    0.96
    orical
    0.96
    onso
    0.95
    oenix
    0.95
    Act Density 0.017%

    No Known Activations