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

    Neuronpedia

    INDEX
    Explanations

    frequent instances of the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.61
    delwed
    -0.57
     berger
    -0.54
    Personendaten
    -0.54
     houſe
    -0.52
     oprot
    -0.52
     objs
    -0.51
    Shepherd
    -0.50
     fons
    -0.50
     depositphotos
    -0.50
    POSITIVE LOGITS
     very
    0.47
     is
    0.45
    AccessorTable
    0.44
    Tikang
    0.42
     largely
    0.42
     ligiloj
    0.41
     highly
    0.41
     oldukça
    0.40
     karar
    0.39
    matchCondition
    0.39
    Act Density 0.522%

    No Known Activations