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

    Neuronpedia

    INDEX
    Explanations

    the word "with" in various contexts

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

    with a preceding descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     matrimon
    -0.31
     Anges
    -0.30
     tromper
    -0.30
    Abstract
    -0.28
    navigationItem
    -0.27
    miami
    -0.26
     drept
    -0.26
     eksper
    -0.26
    })_{
    -0.26
    >();
    -0.26
    POSITIVE LOGITS
    RegressionTest
    0.72
    脚注の使い方
    0.71
    verwijspagina
    0.70
    tvguidetime
    0.68
     surla
    0.66
    ThroughAttribute
    0.65
     okuyayım
    0.65
    aarrggbb
    0.63
    uxxxx
    0.61
    pushFollow
    0.61
    Act Density 0.188%

    No Known Activations