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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propTypes
    -0.54
    multiple
    -0.48
     skry
    -0.47
    some
    -0.47
    Random
    -0.46
    reuters
    -0.45
     Harz
    -0.45
     Cubans
    -0.45
    Boca
    -0.44
     nicio
    -0.44
    POSITIVE LOGITS
    principalTable
    0.95
     الجديد
    0.90
     new
    0.87
    SourceChecksum
    0.86
     kasarigan
    0.86
     новом
    0.82
     nieuwe
    0.80
     новый
    0.79
     nowej
    0.78
    yntaxException
    0.77
    Act Density 0.228%

    No Known Activations