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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social activism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ItemLevel
    -0.65
    Untitled
    -0.65
    ayn
    -0.64
     [[
    -0.63
    Eva
    -0.62
    ("
    -0.61
    $.
    -0.60
    ((
    -0.57
    Interstitial
    -0.57
     whereas
    -0.57
    POSITIVE LOGITS
    ':
    0.81
    '?
    0.81
    ?:
    0.76
     Concern
    0.70
     Approach
    0.69
     Continued
    0.68
    ¶
    0.67
     Costs
    0.67
     Replay
    0.66
     Increasing
    0.65
    Act Density 0.798%

    No Known Activations