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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a decision or choice

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating personal responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hello
    -0.78
    isky
    -0.74
    iked
    -0.70
    mol
    -0.67
    anguages
    -0.67
    ense
    -0.67
    TEXT
    -0.67
    listed
    -0.66
    artifacts
    -0.66
    ãĥŁ
    -0.66
    POSITIVE LOGITS
     discretion
    1.07
     whoever
    0.91
     imagination
    0.83
     interpretation
    0.83
     judges
    0.81
     policymakers
    0.81
     professionals
    0.80
     Allaah
    0.77
     consumers
    0.74
     shoulders
    0.73
    Act Density 0.180%

    No Known Activations