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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or apostrophes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bask
    -0.70
    ConstraintMaker
    -0.69
    Искәрмәләр
    -0.67
     ThemeData
    -0.62
    offsetof
    -0.61
    EndProject
    -0.60
    WebServlet
    -0.59
    iseite
    -0.59
     Rosenthal
    -0.59
    ValueStyle
    -0.58
    POSITIVE LOGITS
    s
    1.07
    €™
    0.73
     &'
    0.68
    \'
    0.60
    ll
    0.60
    %'
    0.59
     '`
    0.58
    =='
    0.56
    ]'
    0.55
    t
    0.55
    Act Density 0.228%

    No Known Activations