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

    Neuronpedia

    INDEX
    Explanations

    personal relationships and emotional connections to experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.86
     their
    -0.62
     ponerse
    -0.61
    toMatchSnapshot
    -0.61
    
    -0.59
     sich
    -0.59
    ="@+
    -0.59
     zich
    -0.57
    กัน
    -0.57
     داشتند
    -0.54
    POSITIVE LOGITS
     myself
    1.63
    myself
    1.36
     Myself
    1.23
     myſelf
    1.01
     my
    0.90
     خودم
    0.89
     говорю
    0.86
    我自己
    0.86
     mijn
    0.78
    Myself
    0.77
    Act Density 1.948%

    No Known Activations