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

    Neuronpedia

    INDEX
    Explanations

    references to innocence

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the term "innocent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.92
    Recomm
    -0.85
    KEY
    -0.76
    ingo
    -0.74
    orders
    -0.73
    ridor
    -0.72
    TOP
    -0.70
    ension
    -0.70
    è¦ļéĨĴ
    -0.69
    ETA
    -0.68
    POSITIVE LOGITS
     innocent
    1.28
     bystand
    1.24
     bystanders
    1.15
     innocence
    1.03
    ocent
    0.94
     innoc
    0.83
     minded
    0.79
     civilians
    0.77
     Innocent
    0.72
     mole
    0.71
    Act Density 0.008%

    No Known Activations