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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atoi
    -0.17
    oho
    -0.16
    ictor
    -0.16
    885
    -0.15
    ura
    -0.14
    orne
    -0.14
    edar
    -0.13
    988
    -0.13
    ascar
    -0.13
    874
    -0.13
    POSITIVE LOGITS
    lech
    0.18
     finally
    0.17
    rozen
    0.17
    rahim
    0.17
    eres
    0.16
    suffix
    0.16
    Lastly
    0.16
     surre
    0.15
     etc
    0.15
    utow
    0.15
    Act Density 0.257%

    No Known Activations