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

    Neuronpedia

    INDEX
    Explanations

    discussions about social justice and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undy
    -0.16
    olan
    -0.15
    odo
    -0.14
    ascar
    -0.14
    olas
    -0.14
    anship
    -0.14
    reo
    -0.14
    olith
    -0.14
    ola
    -0.14
    okino
    -0.14
    POSITIVE LOGITS
     resistance
    0.21
     exempt
    0.20
     exemptions
    0.18
     null
    0.18
     exceptions
    0.18
    null
    0.17
     alternative
    0.17
     modifying
    0.17
     exemption
    0.17
     opposing
    0.17
    Act Density 0.131%

    No Known Activations