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

    Neuronpedia

    INDEX
    Explanations

    legal terms and conditions related to software licenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oredCriteria
    -1.47
     tartalomajánló
    -1.31
     <=",
    -1.31
    InstrumentedTest
    -1.12
    matchCondition
    -1.06
    存于互联网档案馆
    -1.05
     Мексичка
    -1.05
     ModelExpression
    -1.04
     myſelf
    -1.00
     Theſe
    -1.00
    POSITIVE LOGITS
     
    0.50
     C
    0.47
    <eos>
    0.47
     c
    0.47
    di
    0.46
    \
    0.45
     has
    0.44
    .
    0.43
    [
    0.43
    unga
    0.42
    Act Density 0.261%

    No Known Activations