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

    Neuronpedia

    INDEX
    Explanations

    phrases related to close relationships or similarities

    oai_token-act-pair · gpt-3.5-turbo

    the term "closely" in various contexts indicating relationships or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inous
    -0.79
    acity
    -0.74
     Freak
    -0.72
     abundantly
    -0.71
    rers
    -0.67
     vividly
    -0.64
    acious
    -0.63
    eva
    -0.62
    itionally
    -0.62
    plain
    -0.62
    POSITIVE LOGITS
     resembled
    1.06
     allied
    1.06
     aligned
    1.04
     guarded
    1.03
     resemble
    1.02
     resembling
    1.01
     intertwined
    1.01
     linked
    1.00
     resembles
    1.00
     monitored
    1.00
    Act Density 0.046%

    No Known Activations