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

    Neuronpedia

    INDEX
    Explanations

    phrases and statements that express personal opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.77
    
    -0.75
     themselves
    -0.74
     ponerse
    -0.73
    transQ
    -0.71
    pédie
    -0.64
    CloseOperation
    -0.64
     Lordships
    -0.63
    Референце
    -0.62
    ynı
    -0.61
    POSITIVE LOGITS
     myself
    1.43
    myself
    1.18
     Myself
    0.99
     my
    0.87
     myſelf
    0.82
     minhas
    0.78
    my
    0.74
    我自己
    0.72
     mojej
    0.71
     خودم
    0.69
    Act Density 1.605%

    No Known Activations