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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and emotional states

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

    my book, my name, I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.64
    ſſung
    -0.62
     autorytatywna
    -0.61
     ſeveral
    -0.59
    ロウィン
    -0.58
    ðsíða
    -0.57
    aarrggbb
    -0.57
     Eſ
    -0.57
     Efq
    -0.57
     ſol
    -0.56
    POSITIVE LOGITS
     sarili
    0.36
    staw
    0.32
    自己
    0.31
     meinen
    0.29
    VersionUID
    0.28
     myself
    0.28
    alao
    0.27
     me
    0.27
     my
    0.27
    ness
    0.26
    Act Density 0.152%

    No Known Activations