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

    Neuronpedia

    INDEX
    Explanations

    references to spokespersons or spokespeople

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    en
    -0.63
     de
    -0.61
     Se
    -0.61
     se
    -0.60
     K
    -0.60
     Sa
    -0.58
     
    -0.58
     sa
    -0.58
     er
    -0.58
    rec
    -0.58
    POSITIVE LOGITS
     Jefus
    1.38
     myſelf
    1.35
     Spokes
    1.30
     spokesperson
    1.29
     itſelf
    1.29
     spokesman
    1.23
     greateſt
    1.22
     spokespersons
    1.22
     Monfieur
    1.21
     pleaſure
    1.21
    Act Density 0.063%

    No Known Activations