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

    Neuronpedia

    INDEX
    Explanations

    mentions of innocence, often in legal or justice-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    the concept of innocence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Recomm
    -0.81
    orders
    -0.76
    anwhile
    -0.74
    ippers
    -0.74
    need
    -0.73
    emetery
    -0.72
    KEY
    -0.71
     fever
    -0.70
    acter
    -0.69
    division
    -0.69
    POSITIVE LOGITS
     bystand
    1.24
     innocent
    1.21
     bystanders
    1.17
     innocence
    1.06
    ocent
    0.95
     Innocent
    0.83
     innoc
    0.78
     minded
    0.76
     civilians
    0.75
     mole
    0.72
    Act Density 0.011%

    No Known Activations