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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms, particularly relating to personal experiences or situations

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

    contractions like it's and you're

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.66
     الحره
    -0.66
    DllImport
    -0.63
     esternos
    -0.61
    lgari
    -0.60
    MLLoader
    -0.58
    DeleteBehavior
    -0.58
    лерея
    -0.57
    のだろうか
    -0.57
    aarrggbb
    -0.56
    POSITIVE LOGITS
     yourself
    0.83
     your
    0.78
     you
    0.68
     Your
    0.65
    Your
    0.64
     GIPHY
    0.58
     Découvrez
    0.56
     best
    0.55
    What
    0.54
     What
    0.53
    Act Density 0.049%

    No Known Activations