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

    Neuronpedia

    INDEX
    Explanations

    uses of the word "with" adjacent to nouns and math terms.

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     with
    -0.75
    with
    -0.61
     wth
    -0.58
    bootstrapcdn
    -0.56
    With
    -0.54
     WITH
    -0.52
    <bos>
    -0.52
     avec
    -0.51
     With
    -0.50
    seteq
    -0.48
    POSITIVE LOGITS
     betweenstory
    0.68
    omitempty
    0.67
    RetentionPolicy
    0.65
    rawDesc
    0.63
     CreateTagHelper
    0.62
    ollectionView
    0.59
    Datuak
    0.56
    qtype
    0.56
    $\#
    0.56
    vast
    0.55
    Act Density 18.778%

    No Known Activations