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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and prepositions indicating relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acco
    -0.15
    tam
    -0.15
     cor
    -0.15
    dub
    -0.15
     Cou
    -0.15
    oppel
    -0.14
    acon
    -0.14
    γÏĩ
    -0.14
    ouble
    -0.13
     tend
    -0.13
    POSITIVE LOGITS
    133
    0.17
    飾
    0.17
     Tome
    0.17
    ingers
    0.15
    anke
    0.15
    837
    0.15
    LEGRO
    0.15
    834
    0.15
    alic
    0.14
    οÏħÏĤ
    0.14
    Act Density 0.003%

    No Known Activations