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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ciascuno
    -0.69
     wikipagina
    -0.57
     comigo
    -0.56
    both
    -0.56
    seamnă
    -0.56
     ognuno
    -0.55
     similares
    -0.55
     ciasc
    -0.55
     illustrazione
    -0.54
     normaux
    -0.54
    POSITIVE LOGITS
     same
    1.50
     latter
    1.32
     entire
    1.29
     rest
    1.25
     aforementioned
    1.19
     following
    1.18
     various
    1.15
     vast
    1.14
     most
    1.12
     actual
    1.10
    Act Density 2.883%

    No Known Activations