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

    Neuronpedia

    INDEX
    Explanations

    terms related to potential situations or events

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of potential outcomes or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipline
    -0.83
    ogie
    -0.79
    cloth
    -0.75
    ulu
    -0.74
    antry
    -0.72
    gaard
    -0.72
    car
    -0.71
    hips
    -0.71
    uart
    -0.71
    bows
    -0.70
    POSITIVE LOGITS
     future
    0.93
     unintended
    0.83
     pitfalls
    0.80
     threats
    0.79
     fallout
    0.79
     spoilers
    0.78
     usefulness
    0.77
     futures
    0.76
     adversaries
    0.75
     defect
    0.75
    Act Density 0.029%

    No Known Activations