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

    Neuronpedia

    INDEX
    Explanations

    references to luck and lucky characters

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

    Lucky

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bondale
    -0.54
     BoxDecoration
    -0.49
    amh
    -0.44
     kanssa
    -0.43
     blitt
    -0.43
    fahan
    -0.43
    seteq
    -0.42
     Pillars
    -0.42
     ст
    -0.41
    bardziej
    -0.41
    POSITIVE LOGITS
    Lucky
    2.16
     Lucky
    2.14
    lucky
    2.00
     lucky
    2.00
     LUCK
    1.63
    LUCK
    1.50
     unlucky
    1.43
     Luck
    1.28
    luck
    1.27
    Luck
    1.27
    Act Density 0.005%

    No Known Activations