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

    Neuronpedia

    INDEX
    Explanations

    mentions of castles or the word "isn't"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     general
    -0.59
     formal
    -0.57
     special
    -0.57
     Ges
    -0.54
     official
    -0.50
     service
    -0.50
     wooden
    -0.49
     second
    -0.49
     sur
    -0.49
     separate
    -0.48
    POSITIVE LOGITS
    0.82
    parsedMessage
    0.75
     EconPapers
    0.69
     betweenstory
    0.63
     utafitiHapana
    0.63
    AccessorTable
    0.62
    sizeCache
    0.62
     '\\;'
    0.59
    Izvori
    0.59
     increí
    0.59
    Act Density 0.158%

    No Known Activations