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

    Neuronpedia

    INDEX
    Explanations

    words related to deception and abstraction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palma
    -0.85
     Banten
    -0.85
    OCCURRED
    -0.80
     Palin
    -0.80
    bereits
    -0.79
     rootReducer
    -0.79
    ništ
    -0.79
     Barth
    -0.78
    substack
    -0.78
    kháu
    -0.78
    POSITIVE LOGITS
    Everybody
    0.85
     kids
    0.83
     everybody
    0.83
    Gimme
    0.82
     Everybody
    0.82
    Somebody
    0.81
     somebody
    0.80
     Somebody
    0.78
    Nobody
    0.76
     Nobody
    0.72
    Act Density 0.200%

    No Known Activations