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

    Neuronpedia

    INDEX
    Explanations

    interesting events, decisions, or developments in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    uts
    -1.09
    aper
    -0.99
    otent
    -0.96
    utable
    -0.95
    helle
    -0.94
    vr
    -0.93
    hent
    -0.92
    eded
    -0.90
    apers
    -0.89
    reditation
    -0.89
    POSITIVE LOGITS
    ioned
    1.21
     Flavoring
    1.14
     tid
    1.13
     twists
    1.08
     sidel
    1.05
    arios
    1.02
    ly
    1.01
     trivia
    0.99
     insights
    0.98
    andum
    0.96
    Act Density 1.075%

    No Known Activations