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

    Neuronpedia

    INDEX
    Explanations

    concepts related to critical theories and social justice movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reputation
    -0.16
     execut
    -0.15
     Sentinel
    -0.15
    ouro
    -0.14
    oine
    -0.14
     Homo
    -0.14
    uled
    -0.14
    ursed
    -0.14
     Sequence
    -0.13
    rott
    -0.13
    POSITIVE LOGITS
     situated
    0.21
     oppressive
    0.20
     oppression
    0.20
     oppress
    0.19
     standpoint
    0.19
     Paulo
    0.18
     located
    0.18
     intersection
    0.18
     raced
    0.18
    hooks
    0.18
    Act Density 0.081%

    No Known Activations