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

    Neuronpedia

    INDEX
    Explanations

    references to roles of power and authority in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Algon
    -0.52
     MCS
    -0.51
     hypoch
    -0.50
     Shawnee
    -0.49
    Waga
    -0.48
    MCS
    -0.48
     CPF
    -0.47
    サル
    -0.47
     Eisenbahn
    -0.46
    TypedValue
    -0.46
    POSITIVE LOGITS
     Targ
    0.99
     Wester
    0.96
     Dany
    0.88
     Arya
    0.84
    Wester
    0.82
     Jon
    0.79
     Ty
    0.78
     Robb
    0.75
     Jaime
    0.75
     targ
    0.74
    Act Density 0.165%

    No Known Activations