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

    Neuronpedia

    INDEX
    Explanations

    solar panels

    oai_token-act-pair · gpt-3.5-turbo

    references to solar panels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENSE
    -0.79
    EE
    -0.78
     Dee
    -0.76
    GET
    -0.75
    DIT
    -0.75
    sie
    -0.74
    ERE
    -0.73
    oslov
    -0.73
    PUT
    -0.71
     Hol
    -0.71
    POSITIVE LOGITS
     panels
    1.60
    panel
    1.09
     panel
    1.08
    illions
    0.95
     baskets
    0.94
    Panel
    0.93
     brill
    0.93
     racks
    0.91
     bars
    0.90
    hooting
    0.89
    Act Density 0.013%

    No Known Activations