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

    Neuronpedia

    INDEX
    Explanations

    references to uniqueness and distinctive qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    harusnya
    -0.60
     препратки
    -0.59
     Económica
    -0.58
    astéroïdes
    -0.56
    middels
    -0.55
    okovic
    -0.51
     frattempo
    -0.51
    ünste
    -0.50
    RegressionTest
    -0.50
    tidaknya
    -0.49
    POSITIVE LOGITS
     unique
    1.73
    unique
    1.51
     uniqueness
    1.46
     Unique
    1.41
    Unique
    1.38
     uniquely
    1.34
     UNIQUE
    1.27
     unusual
    1.23
    UNIQUE
    1.15
     unik
    1.15
    Act Density 0.301%

    No Known Activations