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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "brought"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.71
    grading
    -0.67
    dating
    -0.67
    livious
    -0.66
    enture
    -0.63
    etheless
    -0.63
     distingu
    -0.62
     transformer
    -0.62
    ede
    -0.62
    bi
    -0.62
    POSITIVE LOGITS
     forth
    0.97
     ashore
    0.78
     forward
    0.76
     up
    0.73
    unity
    0.72
    bring
    0.72
     together
    0.72
    backs
    0.71
     hither
    0.67
    Back
    0.66
    Act Density 0.032%

    No Known Activations