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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of betrayal

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "tra" related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     env
    -1.33
    env
    -1.07
    Msg
    -0.72
     Diesel
    -0.71
    ãĤ¡
    -0.69
    adium
    -0.68
     Neighborhood
    -0.68
     Driver
    -0.67
    offer
    -0.67
     Lane
    -0.67
    POSITIVE LOGITS
     tra
    2.71
     ty
    1.67
     squat
    1.35
     clamp
    0.97
     squats
    0.94
     transgress
    0.93
     swoop
    0.92
     nar
    0.88
     li
    0.88
     repetition
    0.86
    Act Density 0.034%

    No Known Activations