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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     insertions
    -0.42
     OTHERS
    -0.42
     apron
    -0.42
     slike
    -0.42
     spots
    -0.42
     ferons
    -0.41
     ulter
    -0.39
     bir
    -0.39
    etc
    -0.38
     superficial
    -0.38
    POSITIVE LOGITS
     the
    0.73
     either
    0.59
     our
    0.59
     both
    0.58
     another
    0.56
     betrekking
    0.54
    的是
    0.52
    verwijspagina
    0.50
     behalf
    0.50
     his
    0.50
    Act Density 1.253%

    No Known Activations