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

    Neuronpedia

    INDEX
    Explanations

    references to the Secret Service

    oai_token-act-pair · gpt-3.5-turbo

    references to the Secret Service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.93
     brim
    -0.85
    ©¶æ
    -0.72
    tics
    -0.72
    itsch
    -0.71
    odcast
    -0.71
    ulf
    -0.66
    aquin
    -0.65
    gaard
    -0.62
    days
    -0.61
    POSITIVE LOGITS
    Secret
    1.15
    ariat
    1.08
     Secret
    0.95
    secret
    0.93
    marine
    0.86
    rets
    0.84
     Sauce
    0.81
     Secrets
    0.78
    ulously
    0.77
    itud
    0.75
    Act Density 0.009%

    No Known Activations