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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their various applications in sentence structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     they
    -0.66
     comunicarse
    -0.56
     они
    -0.52
    ísimo
    -0.52
    volezza
    -0.52
     tillsammans
    -0.50
     basado
    -0.50
     she
    -0.49
     basé
    -0.49
     вони
    -0.49
    POSITIVE LOGITS
     what
    0.67
     the
    0.64
     either
    0.60
    AISSEE
    0.60
     those
    0.57
     these
    0.56
     việc
    0.56
     them
    0.54
    的是
    0.52
     some
    0.48
    Act Density 1.815%

    No Known Activations