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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to a specific security agency called "Shin Bet"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Shin Bet, the Israeli internal security service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.81
    utics
    -0.78
    utic
    -0.73
    aneers
    -0.71
    rency
    -0.70
    gently
    -0.69
     Pwr
    -0.67
    ENC
    -0.67
    nces
    -0.67
    ãĤ¡
    -0.67
    POSITIVE LOGITS
    obi
    0.95
    eless
    0.91
    ning
    0.87
    omi
    0.86
    ook
    0.85
    azi
    0.83
    aman
    0.82
    Shin
    0.81
    wa
    0.79
    ners
    0.75
    Act Density 0.011%

    No Known Activations