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

    Neuronpedia

    INDEX
    Explanations

    words related to individuals providing protection or security services

    oai_token-act-pair · gpt-3.5-turbo

    references to guards and related security personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pitch
    -0.65
     dreams
    -0.64
     votes
    -0.64
     pitches
    -0.63
     Plat
    -0.61
    OTA
    -0.61
     Bloom
    -0.59
     MX
    -0.59
    aney
    -0.59
     scal
    -0.58
    POSITIVE LOGITS
    guard
    4.81
    guards
    3.84
    Guard
    2.27
     guard
    1.79
     Guard
    1.73
     Guards
    1.40
     guards
    1.34
     Guardian
    1.22
     guardian
    1.12
    breaker
    1.07
    Act Density 0.012%

    No Known Activations