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

    Neuronpedia

    INDEX
    Explanations

    references to race and discussions around historical racial dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.65
    awaiter
    -0.57
    SequentialGroup
    -0.56
    Aktualisiert
    -0.54
    に通
    -0.50
     cias
    -0.49
    capsulation
    -0.49
     newBuilder
    -0.49
     chiunque
    -0.48
    Slf
    -0.47
    POSITIVE LOGITS
     dominate
    0.81
     dominating
    0.74
     dominance
    0.73
    anteil
    0.71
     contribution
    0.71
     outnumbered
    0.70
     disproportion
    0.68
     participation
    0.68
     predominate
    0.67
     CONTRIBUTION
    0.67
    Act Density 0.457%

    No Known Activations