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

    Neuronpedia

    INDEX
    Explanations

    mentions of technical specifications and features related to electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.75
    vae
    -0.72
    ocious
    -0.72
    izen
    -0.70
    rio
    -0.67
    acas
    -0.67
    iots
    -0.66
    sein
    -0.66
    dden
    -0.66
    thood
    -0.65
    POSITIVE LOGITS
     though
    1.45
     although
    1.42
     but
    1.32
     however
    1.17
     whereas
    1.16
     albeit
    1.07
    though
    1.04
     meaning
    1.03
     hence
    1.02
    although
    0.99
    Act Density 0.378%

    No Known Activations