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

    Neuronpedia

    INDEX
    Explanations

    days of the week

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outs
    -0.70
    thood
    -0.67
    à©
    -0.60
    alla
    -0.59
     Solitaire
    -0.57
    isi
    -0.56
    ictionary
    -0.56
    icative
    -0.53
    pread
    -0.52
    gain
    -0.52
    POSITIVE LOGITS
     same
    1.08
     quickest
    1.05
     hardest
    1.02
     longest
    1.02
     next
    1.02
     following
    1.01
    ses
    0.99
     night
    0.98
     moment
    0.97
     day
    0.96
    Act Density 0.098%

    No Known Activations