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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their associations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.15
    asta
    -0.14
     another
    -0.14
    ritt
    -0.14
    Cpp
    -0.14
     což
    -0.14
    umble
    -0.13
    again
    -0.13
    another
    -0.13
     Another
    -0.13
    POSITIVE LOGITS
     each
    0.19
     chaque
    0.17
     successful
    0.17
     InitializeComponent
    0.16
    .backward
    0.15
     кажд
    0.14
    ohn
    0.14
    each
    0.14
    .each
    0.14
     them
    0.14
    Act Density 0.315%

    No Known Activations