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

    Neuronpedia

    INDEX
    Explanations

    words related to surveillance, observation, or investigation

    oai_token-act-pair · gpt-3.5-turbo

    actions and activities related to investigation or observation technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quart
    -0.76
     quart
    -0.71
    construct
    -0.69
     reluct
    -0.69
     spons
    -0.65
     offic
    -0.64
     congr
    -0.63
    appointed
    -0.63
     comprom
    -0.62
     optimism
    -0.62
    POSITIVE LOGITS
    brate
    0.76
    brates
    0.75
     targets
    0.73
    tnc
    0.66
    itored
    0.65
    phas
    0.64
     bushes
    0.63
     him
    0.63
     THEM
    0.63
     Mecca
    0.63
    Act Density 0.590%

    No Known Activations