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

    Neuronpedia

    INDEX
    Explanations

    instances of the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.95
     Monfieur
    -0.94
    CloseOperation
    -0.90
    ^(@)
    -0.90
    WriteTagHelper
    -0.89
     Houſe
    -0.89
     purpoſe
    -0.89
     ſmall
    -0.88
     itſelf
    -0.85
     Theſe
    -0.85
    POSITIVE LOGITS
    ↵↵
    0.50
    o
    0.46
    V
    0.46
    <i>
    0.44
    而出
    0.44
    </b>
    0.43
    ธ์
    0.43
     (
    0.42
    c
    0.42
    N
    0.42
    Act Density 0.502%

    No Known Activations