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

    Neuronpedia

    INDEX
    Explanations

    instances of meetings and interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    secut
    -0.71
    container
    -0.62
    duc
    -0.61
     membranes
    -0.60
     untreated
    -0.60
    ocker
    -0.60
    secution
    -0.60
    wards
    -0.60
     commentary
    -0.60
    vernment
    -0.59
    POSITIVE LOGITS
    amorph
    1.28
    ropolis
    0.98
    agame
    0.93
    tle
    0.90
    ered
    0.78
    ioned
    0.75
    atron
    0.74
    onym
    0.74
    ups
    0.74
    allic
    0.73
    Act Density 0.611%

    No Known Activations