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

    Neuronpedia

    INDEX
    Explanations

    phrases related to innocence or innocence being threatened

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of innocence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    division
    -0.78
    need
    -0.76
    emetery
    -0.73
    ippers
    -0.73
     fever
    -0.72
    Recomm
    -0.72
    artney
    -0.72
    ingo
    -0.71
    KEY
    -0.70
    ularity
    -0.70
    POSITIVE LOGITS
     bystand
    1.27
     bystanders
    1.16
     innocent
    1.12
     innocence
    0.94
    ocent
    0.89
     innoc
    0.78
     minded
    0.77
     civilians
    0.76
     Judith
    0.75
     victims
    0.74
    Act Density 0.019%

    No Known Activations