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

    Neuronpedia

    INDEX
    Explanations

    terms related to linguistic structure and grammar, specifically focusing on modal verbs and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JAR
    -0.49
    組
    -0.40
     campionato
    -0.39
    deel
    -0.39
    ணி
    -0.38
    jar
    -0.38
     thiệu
    -0.38
    ådet
    -0.37
    jeni
    -0.36
     doigts
    -0.36
    POSITIVE LOGITS
     незавершена
    0.86
    Xna
    0.78
    kozá
    0.77
     AssemblyProduct
    0.76
    moiselle
    0.74
    IsMutable
    0.74
    antaranya
    0.73
     Signalez
    0.73
    SBATCH
    0.71
    insee
    0.71
    Act Density 0.073%

    No Known Activations