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

    Neuronpedia

    INDEX
    Explanations

    instances of meetings and interactions between individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     untreated
    -0.69
     membranes
    -0.68
     escaping
    -0.66
     subtract
    -0.64
    recy
    -0.62
    overe
    -0.62
    secution
    -0.61
    otine
    -0.59
    wards
    -0.59
    ciples
    -0.58
    POSITIVE LOGITS
    amorph
    1.12
    ropolis
    0.86
    agame
    0.82
    ioned
    0.80
    ees
    0.76
    atron
    0.75
     Kislyak
    0.70
    Meet
    0.70
     Tanz
    0.70
     Niet
    0.69
    Act Density 1.741%

    No Known Activations