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

    Neuronpedia

    INDEX
    Explanations

    phrases related to questioning motives and intention behind actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.62
    hljs
    -0.58
    oneofs
    -0.57
    IsMutable
    -0.55
    Personendaten
    -0.55
    
    -0.54
    OrFail
    -0.54
    ParallelGroup
    -0.53
    SequentialGroup
    -0.53
    stackSize
    -0.53
    POSITIVE LOGITS
     überhaupt
    0.56
     purpose
    0.55
    RegisterType
    0.54
     AssemblyTitle
    0.54
    Зачем
    0.52
    是为了
    0.50
     Зачем
    0.50
     unnecessary
    0.49
     EconPapers
    0.48
    的目的
    0.47
    Act Density 0.373%

    No Known Activations