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

    Neuronpedia

    INDEX
    Explanations

    repetitions of the word "one" in various contexts

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

    one of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.57
    .*")]
    -0.56
    featureID
    -0.56
    PerformLayout
    -0.56
    rrggbb
    -0.55
    Diweddarwch
    -0.55
    URLException
    -0.54
    });*/
    -0.54
    issors
    -0.52
    RTLI
    -0.52
    POSITIVE LOGITS
     prochains
    0.41
     shared
    0.38
     single
    0.38
     another
    0.38
     One
    0.36
     diffé
    0.36
     favorite
    0.35
    انتهای
    0.35
     aldea
    0.35
    One
    0.35
    Act Density 0.038%

    No Known Activations