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

    Neuronpedia

    INDEX
    Explanations

    instances where the word 'to' is doubled

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISA
    -0.71
    rim
    -0.65
    ellectual
    -0.61
    estic
    -0.60
     rall
    -0.60
    OTE
    -0.59
     Cosponsors
    -0.59
    earable
    -0.59
    rod
    -0.59
    aila
    -0.57
    POSITIVE LOGITS
     2022
    0.79
     2024
    0.76
     2030
    0.71
     2025
    0.71
    ruct
    0.67
     24
    0.67
     2021
    0.67
     onwards
    0.65
     20
    0.64
    ruary
    0.64
    Act Density 1.486%

    No Known Activations