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

    Neuronpedia

    INDEX
    Explanations

    references to unions and advocacy groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     simulator
    -0.71
     hindsight
    -0.70
     Gaal
    -0.67
     bung
    -0.66
     embell
    -0.65
     mastered
    -0.65
     ensu
    -0.64
     arsen
    -0.63
     brilliance
    -0.63
     tumble
    -0.63
    POSITIVE LOGITS
     advocacy
    1.29
     ACLU
    1.07
     advocates
    1.04
     advocating
    1.04
     Advoc
    1.04
     NAACP
    1.02
     coalition
    1.00
     applaud
    0.96
     nonpartisan
    0.95
     Equality
    0.95
    Act Density 0.305%

    No Known Activations