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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    references to time, color, and physical distinctions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sclerosis
    -0.72
    weapons
    -0.63
    aminer
    -0.61
    police
    -0.60
    senal
    -0.60
    aughters
    -0.60
     munitions
    -0.59
    pers
    -0.58
    ourced
    -0.58
     weaponry
    -0.58
    POSITIVE LOGITS
     versus
    0.90
    -,
    0.87
    +,
    0.87
    +
    0.87
     vs
    0.87
    +)
    0.86
     or
    0.85
    /-
    0.85
    /
    0.83
     ->
    0.80
    Act Density 0.370%

    No Known Activations