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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or approximations of quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    βο
    -0.17
    illis
    -0.17
    assed
    -0.16
    agne
    -0.15
    urst
    -0.15
    oom
    -0.14
    .allocate
    -0.14
    allet
    -0.14
    edia
    -0.14
    ataka
    -0.14
    POSITIVE LOGITS
     dozens
    0.20
    aits
    0.17
     altogether
    0.16
     myriad
    0.16
     many
    0.15
    çľ¾
    0.15
     TF
    0.15
     dozen
    0.15
     Principle
    0.14
    riere
    0.14
    Act Density 0.084%

    No Known Activations