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

    Neuronpedia

    INDEX
    Explanations

    references to strikes and labor unions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TAINMENT
    -0.88
    cemment
    -0.81
    phorbia
    -0.79
     Mainz
    -0.79
    mybatisplus
    -0.78
    DataAnnotations
    -0.75
    waard
    -0.75
    ttemberg
    -0.73
     Lizzy
    -0.71
     Polri
    -0.70
    POSITIVE LOGITS
     Strikes
    1.29
     strikes
    1.21
     strike
    1.14
     Strike
    1.08
    Strike
    1.07
     striking
    0.99
     Stripes
    0.99
    Piper
    0.92
    strike
    0.91
     Piper
    0.90
    Act Density 0.492%

    No Known Activations