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

    Neuronpedia

    INDEX
    Explanations

    names of locations and words related to legal disputes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.85
    ividual
    -0.82
    acca
    -0.73
    etheless
    -0.73
    aneers
    -0.73
    ãĥ¼ãĥĨ
    -0.69
    raints
    -0.69
    ilities
    -0.67
    ãģĨ
    -0.66
    ����
    -0.66
    POSITIVE LOGITS
    isure
    1.27
    agues
    1.14
    opard
    1.12
    ukemia
    1.06
    lean
    1.00
    icester
    0.99
    vered
    0.96
    aping
    0.94
    utenant
    0.93
    vity
    0.92
    Act Density 0.418%

    No Known Activations