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

    Neuronpedia

    INDEX
    Explanations

    references to a specific organization called "Shin Bet."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Shin Bet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.82
    utics
    -0.76
    aneers
    -0.73
    rency
    -0.71
    utic
    -0.70
    gently
    -0.70
    ENCE
    -0.68
    enance
    -0.68
    ENC
    -0.67
    nces
    -0.67
    POSITIVE LOGITS
    obi
    1.02
    eless
    0.88
    ook
    0.87
    omi
    0.86
    ning
    0.85
    wa
    0.83
    azi
    0.82
    Shin
    0.81
    aman
    0.80
    ichi
    0.80
    Act Density 0.017%

    No Known Activations