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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Sunshine" with a high activation value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "Sunshine" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rodu
    -0.71
    ideo
    -0.69
    grave
    -0.68
    hist
    -0.68
    gra
    -0.68
    aleb
    -0.67
    eport
    -0.66
    burg
    -0.65
     targ
    -0.65
    gru
    -0.65
    POSITIVE LOGITS
     Sunshine
    4.25
     sunshine
    1.89
    shine
    1.59
     Sunrise
    1.20
     Darling
    1.18
    noon
    1.14
     Peach
    1.02
     Shine
    1.00
     Mayo
    1.00
    flower
    0.91
    Act Density 0.038%

    No Known Activations