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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Sugar"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Sugar" and "Sweet" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     posit
    -0.78
     regener
    -0.76
     dh
    -0.73
    REM
    -0.73
     commun
    -0.73
     foc
    -0.71
     detach
    -0.71
     ax
    -0.71
     radi
    -0.71
     cath
    -0.70
    POSITIVE LOGITS
     Sugar
    3.51
     Sug
    1.98
     Sweet
    1.90
     Cotton
    1.81
    ugar
    1.70
    Sweet
    1.63
     Candy
    1.40
     Grape
    1.36
     Soda
    1.35
     Honey
    1.29
    Act Density 0.029%

    No Known Activations