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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and adverbs indicating spatial relationships or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocument
    -0.71
    avorite
    -0.64
    perty
    -0.63
    Tes
    -0.63
    natureconservancy
    -0.61
    merce
    -0.61
    ample
    -0.60
    inctions
    -0.60
    rosso
    -0.59
    mares
    -0.58
    POSITIVE LOGITS
     standpoint
    1.21
     vantage
    1.09
     outset
    1.01
     perspective
    0.98
     sources
    0.89
     onwards
    0.89
     inception
    0.84
     perspectives
    0.83
    ratch
    0.83
     viewpoint
    0.83
    Act Density 0.290%

    No Known Activations