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

    Neuronpedia

    INDEX
    Explanations

    terms related to controlled environments or substances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Honour
    -0.81
     Kinnikuman
    -0.69
    owe
    -0.69
    elt
    -0.67
    hire
    -0.67
    eds
    -0.66
    ople
    -0.65
    é¾įåĸļ士
    -0.65
    icken
    -0.64
    older
    -0.64
    POSITIVE LOGITS
     controlled
    0.90
     substances
    0.84
     airspace
    0.79
    rador
    0.76
    eer
    0.75
     demolition
    0.72
    eering
    0.71
    controlled
    0.71
     contro
    0.70
     freak
    0.69
    Act Density 0.033%

    No Known Activations