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

    Neuronpedia

    INDEX
    Explanations

    spy-related words

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spying or surveillance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pite
    -0.77
    hirt
    -0.72
    rawn
    -0.67
    inished
    -0.66
    ension
    -0.65
    urdue
    -0.63
     condensed
    -0.63
     separation
    -0.62
     sob
    -0.61
     ribbon
    -0.60
    POSITIVE LOGITS
    hawk
    0.87
    onom
    0.78
    finder
    0.78
     Aware
    0.77
     Detect
    0.76
    ostics
    0.75
    rors
    0.74
     seeker
    0.73
     Watch
    0.72
     spies
    0.71
    Act Density 0.071%

    No Known Activations