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

    Neuronpedia

    INDEX
    Explanations

    mentions of boycotts

    oai_token-act-pair · gpt-3.5-turbo

    references to boycott-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -0.87
     confir
    -0.87
     exha
    -0.83
     srf
    -0.79
     actu
    -0.79
    nesota
    -0.78
     planner
    -0.77
     concurrent
    -0.76
    senal
    -0.76
    ¥ŀ
    -0.75
    POSITIVE LOGITS
    cott
    1.64
    ijn
    0.93
    ages
    0.87
    wright
    0.87
    ione
    0.86
    riott
    0.84
    ieu
    0.83
    aign
    0.83
    olkien
    0.82
    ards
    0.82
    Act Density 0.008%

    No Known Activations