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

    Neuronpedia

    INDEX
    Explanations

    references to sports players and their performance

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

    Tokens preceding "improve"

    np_acts-logits-general · gemini-2.0-flash

    improvement and growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "]').
    -0.55
    (;;)
    -0.53
     éduc
    -0.50
     taus
    -0.49
     épais
    -0.49
     "'");
    -0.49
    rø
    -0.48
    既
    -0.48
     Walpole
    -0.47
    Victory
    -0.47
    POSITIVE LOGITS
     shine
    0.71
     consistency
    0.67
     blossoming
    0.65
     performing
    0.65
     blossomed
    0.64
     shines
    0.63
    Consistency
    0.63
     inconsistency
    0.63
     maturing
    0.63
     consistently
    0.63
    Act Density 0.211%

    No Known Activations