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

    Neuronpedia

    INDEX
    Explanations

    names of historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brandi
    -0.64
     Gabi
    -0.64
     Cassie
    -0.63
    -0.62
     spett
    -0.58
     Mistress
    -0.58
     Jodi
    -0.58
     cristina
    -0.57
     Citadel
    -0.57
     Renegade
    -0.57
    POSITIVE LOGITS
     Charles
    1.18
     William
    1.15
     Robert
    1.09
     Edward
    1.07
     Henry
    1.05
    Charles
    0.99
     Philip
    0.96
     George
    0.95
     Samuel
    0.94
     James
    0.93
    Act Density 0.510%

    No Known Activations