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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "photovoltaic" often abbreviated to "photovolt" with numerical values following it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the string "ov"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prevail
    -0.68
    dress
    -0.66
    arthed
    -0.66
    fix
    -0.63
    Ĥª
    -0.63
     McKay
    -0.59
     cane
    -0.59
     prevailing
    -0.59
     womb
    -0.58
    ometimes
    -0.58
    POSITIVE LOGITS
    ski
    1.34
    irus
    1.10
    ille
    1.09
    ideo
    1.07
    itz
    1.05
    oice
    1.00
    olt
    0.99
    rolet
    0.99
    iew
    0.95
    itch
    0.93
    Act Density 0.023%

    No Known Activations