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

    Neuronpedia

    INDEX
    Explanations

    information regarding the location or presence of certain items or substances

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prepositional phrase "in" particularly to highlight location or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    —-
    -0.74
     indebted
    -0.68
    ZA
    -0.68
    leep
    -0.66
     reliant
    -0.65
    ihad
    -0.62
    LOG
    -0.62
     embold
    -0.61
    ilege
    -0.60
     obliged
    -0.59
    POSITIVE LOGITS
    ordinate
    1.16
     conjunction
    1.16
    humane
    1.08
    animate
    1.07
     lieu
    1.06
    roads
    1.05
     accordance
    1.04
    effic
    1.04
    clusions
    1.03
    organic
    1.02
    Act Density 0.331%

    No Known Activations