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

    Neuronpedia

    INDEX
    Explanations

    linguistic markers and connectives that indicate structure or relationships in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fa
    -0.36
     Ch
    -0.34
     devoirs
    -0.33
     li
    -0.31
     ch
    -0.30
     і
    -0.29
     Com
    -0.28
    स्य
    -0.28
     Det
    -0.28
     sim
    -0.28
    POSITIVE LOGITS
    complexContent
    0.87
     InputDecoration
    0.77
    MLLoader
    0.76
     consultato
    0.75
     estadounid
    0.74
    parsedMessage
    0.73
     ſeine
    0.73
    ſchen
    0.72
     increí
    0.71
    ðsíða
    0.71
    Act Density 0.332%

    No Known Activations