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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location or time

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in" and its occurrences throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    object
    -0.67
    Owner
    -0.66
    rang
    -0.63
    ãĥīãĥ©
    -0.63
    =#
    -0.62
    orem
    -0.62
    tal
    -0.62
    hemy
    -0.61
    GAN
    -0.61
    Text
    -0.61
    POSITIVE LOGITS
     vitro
    1.03
     lieu
    0.99
     accordance
    0.95
     regards
    0.89
     terms
    0.83
     conjunction
    0.81
     anticipation
    0.79
     Calais
    0.78
    versions
    0.77
     hopes
    0.75
    Act Density 0.428%

    No Known Activations