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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "both."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     qualunque
    -0.71
    either
    -0.69
     either
    -0.67
    Either
    -0.64
     entweder
    -0.64
     Either
    -0.63
     tamén
    -0.60
     vaikka
    -0.60
    Alguien
    -0.59
     anywhere
    -0.59
    POSITIVE LOGITS
     sides
    1.36
    sides
    1.07
     sexes
    0.99
     Sides
    0.91
     ends
    0.90
     kinds
    0.85
     halves
    0.85
     parties
    0.81
    Sides
    0.78
     Seiten
    0.70
    Act Density 0.129%

    No Known Activations