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

    Neuronpedia

    INDEX
    Explanations

    titles and forms of address in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.99
    ſelves
    -0.91
     صوتيه
    -0.82
     لينك
    -0.79
    SequentialGroup
    -0.78
    istoitu
    -0.77
     تضيفلها
    -0.77
     متعلقه
    -0.76
    RenderAtEndOf
    -0.75
     itſelf
    -0.75
    POSITIVE LOGITS
    ,
    0.54
    !
    0.49
     boys
    0.47
     bonne
    0.47
     Sir
    0.45
    よ
    0.44
     boy
    0.43
     guys
    0.43
     Boy
    0.42
     Sc
    0.42
    Act Density 0.087%

    No Known Activations