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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social activism and advocacy

    oai_token-act-pair · gpt-3.5-turbo

    clauses expressing moral or ethical principles related to individual rights and social responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ety
    -0.73
    iple
    -0.67
     sheet
    -0.62
    raft
    -0.61
    OND
    -0.61
    cott
    -0.57
    ©¶æ
    -0.57
    UF
    -0.57
    ovember
    -0.56
    USS
    -0.56
    POSITIVE LOGITS
     albeit
    1.21
     namely
    1.16
     irrespective
    1.11
     regardless
    1.11
     etc
    1.01
     whereas
    1.01
     thereby
    1.00
     lest
    0.99
     culminating
    0.93
     aka
    0.93
    Act Density 0.767%

    No Known Activations