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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating a specific location or time

    oai_token-act-pair · gpt-3.5-turbo

    references to time and location in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.54
     Uzbek
    -0.53
     fut
    -0.52
    anto
    -0.51
    Cub
    -0.51
     pact
    -0.50
    iant
    -0.49
    yo
    -0.49
    STEM
    -0.48
     Billion
    -0.47
    POSITIVE LOGITS
    éĹĺ
    0.64
     itself
    0.59
    pers
    0.58
    ixel
    0.57
    notations
    0.56
    athi
    0.54
    hesion
    0.54
    mins
    0.54
     convey
    0.53
    ighting
    0.53
    Act Density 1.102%

    No Known Activations