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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     kos
    -0.54
    SuspendLayout
    -0.52
     saud
    -0.52
    τω
    -0.50
    ulite
    -0.48
     Preview
    -0.47
    Kos
    -0.47
    tsin
    -0.46
    lwjgl
    -0.46
     PREVIEW
    -0.45
    POSITIVE LOGITS
    CodedInputStream
    0.84
    esez
    0.84
     Roskov
    0.83
    IsMutable
    0.81
    TargetException
    0.81
    AndEndTag
    0.80
     للمعارف
    0.79
    "):
    0.79
    AccessorTable
    0.79
     NSCoder
    0.78
    Act Density 0.005%

    No Known Activations