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

    Neuronpedia

    INDEX
    Explanations

    information related to political events and statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    thought
    -0.65
    Morning
    -0.64
    bidden
    -0.63
    kson
    -0.63
    got
    -0.63
    heard
    -0.63
    Hart
    -0.62
    awed
    -0.62
    arthed
    -0.62
    çīĪ
    -0.62
    POSITIVE LOGITS
     eliminate
    1.42
     minimize
    1.42
     promote
    1.37
     simplify
    1.36
     reduce
    1.35
     stimulate
    1.35
     create
    1.34
     facilitate
    1.34
     cultivate
    1.32
     stabilize
    1.32
    Act Density 1.346%

    No Known Activations