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

    Neuronpedia

    INDEX
    Explanations

    references to "English" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.68
     VIDEOTAPE
    -0.64
    랐
    -0.63
     estekak
    -0.59
     Sacrament
    -0.59
     Magee
    -0.58
     esterni
    -0.58
    יצד
    -0.58
     ricette
    -0.57
     Memoirs
    -0.56
    POSITIVE LOGITS
     English
    2.79
     England
    2.48
    English
    2.45
     english
    2.31
    England
    2.25
     ENGLISH
    2.23
    english
    2.03
     ENGLAND
    1.94
    ENGLISH
    1.91
     england
    1.86
    Act Density 0.062%

    No Known Activations