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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to voting or poll results

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.74
     Hort
    -0.67
    âĹ¼
    -0.62
    sed
    -0.60
    urger
    -0.60
    ophon
    -0.59
     Herz
    -0.58
    ensen
    -0.58
    ppo
    -0.58
    worldly
    -0.58
    POSITIVE LOGITS
    Thirty
    1.16
    âĺħ
    0.87
    010
    0.80
    678
    0.80
    0000
    0.79
     ILCS
    0.79
    th
    0.77
    iam
    0.73
    âĢ²
    0.73
    teen
    0.72
    Act Density 0.116%

    No Known Activations