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

    Neuronpedia

    INDEX
    Explanations

    locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llor
    -0.72
    dule
    -0.70
    NOW
    -0.68
     showc
    -0.68
    76561
    -0.67
    soever
    -0.66
    cas
    -0.62
     exited
    -0.62
     indicated
    -0.61
     accordingly
    -0.61
    POSITIVE LOGITS
    animate
    1.16
    effic
    1.15
    efficiency
    1.09
     situ
    1.06
    clusions
    1.05
     conjunction
    1.03
     spite
    1.00
    roads
    0.98
     lieu
    0.97
     relation
    0.96
    Act Density 0.345%

    No Known Activations