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

    Neuronpedia

    INDEX
    Explanations

    the presence of the letter 'e' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Houſe
    -0.77
    ſelves
    -0.74
     houſe
    -0.71
    ſelf
    -0.70
     Majefty
    -0.66
     itſelf
    -0.64
    </caption>
    -0.63
     Jefus
    -0.61
     discogs
    -0.61
     themſelves
    -0.60
    POSITIVE LOGITS
    :
    0.70
     cioè
    0.68
    tså
    0.67
    즉
    0.65
     gynhyrchwyd
    0.64
    那就是
    0.63
    verwijspagina
    0.63
     Exacts
    0.62
     []:
    0.61
    uket
    0.60
    Act Density 0.272%

    No Known Activations