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

    Neuronpedia

    INDEX
    Explanations

    references to spokespersons and their roles or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.58
    子上
    -0.52
    花板
    -0.50
    онка
    -0.49
     ideas
    -0.48
    점
    -0.48
    teness
    -0.47
     address
    -0.47
     way
    -0.47
     emotion
    -0.46
    POSITIVE LOGITS
     spokesman
    3.97
     spokeswoman
    3.42
     spokesperson
    3.39
     Spokes
    3.09
     spokespersons
    2.30
     spokes
    2.24
     portavoz
    2.11
    Spo
    1.59
    spo
    1.43
     Sprecher
    1.06
    Act Density 0.076%

    No Known Activations