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

    Neuronpedia

    INDEX
    Explanations

    references to breaking news and alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivas
    -0.80
     discriminated
    -0.75
    ngth
    -0.71
    ogh
    -0.69
     Tsukuyomi
    -0.67
    ono
    -0.64
     discriminating
    -0.63
    iless
    -0.63
     discrim
    -0.62
    ogie
    -0.62
    POSITIVE LOGITS
     alerts
    0.81
     Reporting
    0.78
     stories
    0.77
    letter
    0.77
    flash
    0.74
     Synd
    0.74
     Daily
    0.72
     reporter
    0.72
    weekly
    0.71
     headlines
    0.70
    Act Density 0.009%

    No Known Activations