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

    Neuronpedia

    INDEX
    Explanations

    locations or institutions where people work or study

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOW
    -0.70
    untled
    -0.69
     ingred
    -0.69
    ALSE
    -0.67
    sle
    -0.65
     convol
    -0.64
     incumb
    -0.64
    wagon
    -0.64
     unemploy
    -0.63
     innoc
    -0.63
    POSITIVE LOGITS
     conjunction
    1.30
     lieu
    1.27
     accordance
    1.15
    clus
    1.06
    ked
    1.02
    clusions
    1.01
     favor
    1.00
     order
    0.97
     regards
    0.95
    patient
    0.95
    Act Density 0.314%

    No Known Activations