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

    Neuronpedia

    INDEX
    Explanations

    2-syllable adjectives related to light intensity or clarity

    oai_token-act-pair · gpt-3.5-turbo

    references to weakness or lack of intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?????-
    -0.78
    gemony
    -0.76
    enture
    -0.75
     Destruction
    -0.71
    atro
    -0.68
     Hebdo
    -0.65
    FactoryReloaded
    -0.65
     Factors
    -0.62
     DRAG
    -0.62
    ulkan
    -0.62
    POSITIVE LOGITS
    est
    0.93
     faint
    0.92
    ener
    0.89
    lings
    0.81
     glow
    0.79
     violet
    0.78
    ethy
    0.78
     flickering
    0.77
     blinking
    0.76
    light
    0.75
    Act Density 0.025%

    No Known Activations