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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elemField
    -1.00
    oredCriteria
    -0.96
     betweenstory
    -0.96
    __":
    -0.96
    RegistryLite
    -0.94
     Chwiliwch
    -0.94
    OGND
    -0.93
     fieldNum
    -0.92
     kasarigan
    -0.92
    __':
    -0.92
    POSITIVE LOGITS
     middle
    0.57
     match
    0.56
     a
    0.55
     pro
    0.55
    UMBUS
    0.54
     polaire
    0.54
     thin
    0.54
     ευ
    0.53
     
    0.52
     Kier
    0.52
    Act Density 0.023%

    No Known Activations