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
     Efq
    -0.76
     qualunque
    -0.74
    seamnă
    -0.71
     tamén
    -0.70
     négociations
    -0.66
     whoſe
    -0.66
     tantôt
    -0.65
     ſeveral
    -0.64
     cérami
    -0.63
     allemaal
    -0.63
    POSITIVE LOGITS
     sides
    1.50
    sides
    1.21
     sexes
    1.12
     parties
    1.01
     Sides
    0.99
     kinds
    0.96
     ends
    0.95
     halves
    0.90
    Sides
    0.88
     types
    0.83
    Act Density 0.120%

    No Known Activations