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

    Neuronpedia

    INDEX
    Explanations

    conversational expressions and affirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    الدراسه
    -0.94
    >*/
    -0.93
    MLLoader
    -0.92
     betweenstory
    -0.91
    AsUp
    -0.91
     فريبيس
    -0.90
     noqa
    -0.89
    endphp
    -0.89
    Geplaatst
    -0.88
    Cyfeiriadau
    -0.87
    POSITIVE LOGITS
     
    0.63
     I
    0.59
    I
    0.48
    <eos>
    0.48
     General
    0.47
    ↵↵
    0.47
    i
    0.47
    Re
    0.46
     broke
    0.45
    '
    0.44
    Act Density 0.273%

    No Known Activations