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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter 's' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.52
    ↵↵
    -0.50
    ****************
    -0.44
     -
    -0.43
    k
    -0.43
    ****
    -0.42
    ,
    -0.42
    **
    -0.42
    </i>
    -0.41
    ↵↵↵↵
    -0.40
    POSITIVE LOGITS
     dagens
    1.19
    ſelf
    1.19
    ſelves
    1.18
     Jefus
    1.17
     greateſt
    1.16
     fevere
    1.11
     resourceCulture
    1.07
     itſelf
    1.05
     Majefty
    1.04
     Theſe
    1.04
    Act Density 0.113%

    No Known Activations