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

    Neuronpedia

    INDEX
    Explanations

    specific patterns related to hardware features and functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.95
    SequentialGroup
    -0.90
     purpoſe
    -0.81
    expandindo
    -0.80
     Monfieur
    -0.79
     myſelf
    -0.78
     itſelf
    -0.76
     pleaſure
    -0.76
     AppColors
    -0.76
     ſeveral
    -0.74
    POSITIVE LOGITS
     were
    0.50
    fillType
    0.49
     tur
    0.47
    OGND
    0.44
     box
    0.43
     (;;
    0.43
    <bos>
    0.42
     .
    0.42
     turn
    0.42
     coba
    0.42
    Act Density 0.214%

    No Known Activations