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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and documents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "ra"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.75
    icians
    -0.73
    ician
    -0.69
    regor
    -0.66
    lace
    -0.66
    agascar
    -0.64
    alion
    -0.63
     Revel
    -0.61
    orem
    -0.60
    aminer
    -0.60
    POSITIVE LOGITS
    irie
    1.28
    fter
    1.26
    fters
    1.22
    ven
    1.12
    eus
    1.10
    ving
    1.08
    ffiti
    1.08
    zzo
    1.07
    ppa
    1.07
    ffe
    1.07
    Act Density 0.037%

    No Known Activations