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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    withExtended, withConversion, withMonth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.47
    EndInit
    -0.46
    usercontent
    -0.46
     dataSet
    -0.43
    enumi
    -0.42
    tvguidetime
    -0.40
    forRoot
    -0.39
    VersionUID
    -0.39
    :\/\/
    -0.39
    Advertisement
    -0.37
    POSITIVE LOGITS
    With
    0.58
     With
    0.54
    Without
    0.53
    Diwedd
    0.52
     שוליים
    0.49
     Without
    0.49
     mulighed
    0.48
     '\\;'
    0.47
    Whose
    0.47
    ThroughAttribute
    0.46
    Act Density 0.010%

    No Known Activations