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

    Neuronpedia

    INDEX
    Explanations

    instances of prepositions or phrases indicating a relationship between entities

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     =================
    -0.66
     Revis
    -0.65
     Claus
    -0.63
     happily
    -0.62
     âī
    -0.61
     meanwhile
    -0.60
     accommod
    -0.60
     altern
    -0.59
     inn
    -0.57
     emphatically
    -0.56
    POSITIVE LOGITS
    roads
    1.07
    breeding
    1.07
    ings
    1.05
    conom
    1.05
    effic
    1.04
    gs
    1.02
    icular
    1.02
    laws
    1.02
    days
    1.01
    nesses
    1.00
    Act Density 0.517%

    No Known Activations