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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific proper noun, "Chase"

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal or medical terminology, particularly focusing on the term "case" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acies
    -0.88
    arious
    -0.84
    ersive
    -0.82
    icum
    -0.82
    hops
    -0.80
    ersen
    -0.76
    ornia
    -0.76
    ition
    -0.75
    sburgh
    -0.73
    imated
    -0.73
    POSITIVE LOGITS
    xual
    1.92
     inhibitors
    1.01
     inhibitor
    0.91
    lled
    0.89
    ño
    0.89
    lly
    0.84
    lling
    0.81
    lla
    0.80
     Sapphire
    0.73
    ñ
    0.72
    Act Density 0.051%

    No Known Activations