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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals, particularly those involved in significant incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alg
    -0.93
    orb
    -0.84
    inel
    -0.83
    ional
    -0.80
    ropolitan
    -0.79
    abol
    -0.79
    rog
    -0.79
    enced
    -0.78
    gery
    -0.77
    gencies
    -0.77
    POSITIVE LOGITS
     Kelley
    0.79
     Ingram
    0.75
     Hatch
    0.69
     Roof
    0.68
     Preferred
    0.65
     Dunn
    0.64
     Cherokee
    0.64
     Redemption
    0.63
     Fore
    0.60
     Means
    0.60
    Act Density 0.016%

    No Known Activations