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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    transQ
    -0.42
    horabuena
    -0.37
     fiscales
    -0.37
     suelo
    -0.36
     Grecs
    -0.36
     setempat
    -0.35
     acier
    -0.35
     Administr
    -0.35
     abiertos
    -0.34
     boîtier
    -0.34
    POSITIVE LOGITS
    angliski
    0.56
     ffilmiau
    0.55
    And
    0.54
    IndentedString
    0.54
     And
    0.53
    Και
    0.53
    まあ
    0.52
    SBATCH
    0.52
     بيها
    0.51
    Chham
    0.50
    Act Density 0.137%

    No Known Activations