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

    Neuronpedia

    INDEX
    Explanations

    words related to construction and modifications over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.67
     שוליים
    -0.60
    __*/
    -0.59
    ArgsConstructor
    -0.58
    CodedInputStream
    -0.57
    MessageOf
    -0.56
    sizeCache
    -0.56
    HostException
    -0.56
    setVerticalGroup
    -0.54
    complexContent
    -0.54
    POSITIVE LOGITS
     had
    0.57
     wcześ
    0.53
     previamente
    0.52
     había
    0.50
     précédemment
    0.50
     zuvor
    0.49
    mişti
    0.49
     hatte
    0.49
     hadn
    0.49
     auparavant
    0.48
    Act Density 0.636%

    No Known Activations