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

    Neuronpedia

    INDEX
    Explanations

    text related to regulations or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    collective actions or sentiments within a community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.66
     herself
    -0.66
     Digest
    -0.56
     Adolf
    -0.56
    elson
    -0.55
    stroke
    -0.54
    itto
    -0.51
    ented
    -0.50
     rubbed
    -0.49
    Reilly
    -0.49
    POSITIVE LOGITS
     ourselves
    1.58
     our
    1.00
     OUR
    0.86
     ours
    0.84
    Our
    0.76
     asses
    0.74
     Our
    0.72
     selves
    0.68
     collectively
    0.60
    blogs
    0.60
    Act Density 0.957%

    No Known Activations