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

    Neuronpedia

    INDEX
    Explanations

    mentions of sources of light

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "glow" or light-related phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ABE
    -0.77
    ÄŁ
    -0.68
     sshd
    -0.66
    assian
    -0.65
     awoken
    -0.65
     Examination
    -0.62
    arnaev
    -0.62
     Strait
    -0.62
     Debor
    -0.61
     Alps
    -0.61
    POSITIVE LOGITS
    sticks
    0.99
    stick
    0.91
    ingly
    0.88
    stone
    0.87
    dust
    0.86
    stones
    0.85
    pots
    0.84
    itsch
    0.78
    atur
    0.76
    eful
    0.76
    Act Density 0.029%

    No Known Activations