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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of innocence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "innocent" in various contexts related to individuals and human rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.83
    division
    -0.82
    artney
    -0.81
    need
    -0.75
    riber
    -0.74
    emetery
    -0.73
    TOP
    -0.72
    orders
    -0.71
    pain
    -0.69
    hester
    -0.68
    POSITIVE LOGITS
     bystand
    1.27
     bystanders
    1.13
     innocent
    1.09
     innocence
    1.00
    ocent
    0.91
     Judith
    0.79
     innoc
    0.77
     mole
    0.76
     Innocent
    0.75
     civilians
    0.75
    Act Density 0.023%

    No Known Activations