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

    Neuronpedia

    INDEX
    Explanations

    words related to social issues and criticism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAW
    -0.82
    STDOUT
    -0.66
     tab
    -0.64
    apers
    -0.64
     kindred
    -0.63
    versions
    -0.62
    leted
    -0.61
    IAL
    -0.61
    inese
    -0.60
    actionDate
    -0.59
    POSITIVE LOGITS
    terday
    1.61
    hhhh
    1.00
    hhh
    0.90
    hh
    0.85
     sir
    0.83
     pardon
    0.79
     yes
    0.78
     Yeah
    0.76
     yeah
    0.73
    soever
    0.72
    Act Density 1.402%

    No Known Activations