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

    Neuronpedia

    INDEX
    Explanations

    references to Twitter accounts with 'Twe' in their name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Tweezers" or related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĩ
    -0.76
    Downloadha
    -0.73
    inates
    -0.72
    ORED
    -0.71
    inated
    -0.69
     buckle
    -0.67
    STAR
    -0.64
    aimon
    -0.64
    creen
    -0.64
    ARA
    -0.63
    POSITIVE LOGITS
    sburg
    0.87
    aken
    0.84
    eds
    0.84
    leaf
    0.82
    quarters
    0.82
    ²
    0.80
    riter
    0.80
    aking
    0.79
    ety
    0.78
    ller
    0.78
    Act Density 0.034%

    No Known Activations