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

    Neuronpedia

    INDEX
    Explanations

    conclusive or transitional phrases indicating a summary or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eureka
    -1.09
     Bernadette
    -1.06
     Colgate
    -1.05
     Coton
    -1.02
     PFA
    -1.01
     Frankie
    -1.00
     CPF
    -0.98
     Colette
    -0.97
     Apre
    -0.94
     Bambi
    -0.94
    POSITIVE LOGITS
    ly
    1.13
     dần
    0.78
    ς
    0.76
    maßen
    0.73
     учетом
    0.72
    ième
    0.71
    ling
    0.69
     ๆ
    0.67
     учета
    0.66
     thus
    0.66
    Act Density 0.126%

    No Known Activations