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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions and ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.74
     in
    -0.56
    ,
    -0.50
    ãng
    -0.50
    ir
    -0.49
     Y
    -0.49
    ina
    -0.49
     y
    -0.48
     has
    -0.48
    a
    -0.47
    POSITIVE LOGITS
    Geplaatst
    0.98
     \%-
    0.93
     Monfieur
    0.90
    Datuak
    0.84
     ſever
    0.83
     Efq
    0.81
     myſelf
    0.80
     faſt
    0.79
     Савезне
    0.78
    ConstraintMaker
    0.77
    Act Density 0.566%

    No Known Activations