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

    Neuronpedia

    INDEX
    Explanations

    phrases related to licensing and copyright terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rolls
    -0.16
     shel
    -0.15
    éri
    -0.15
     Ft
    -0.15
     Priv
    -0.14
    -0.14
    fy
    -0.14
     roll
    -0.14
     gang
    -0.14
    erto
    -0.14
    POSITIVE LOGITS
    ANO
    0.15
    deaux
    0.15
    ãĥ«ãĥĪ
    0.15
    astle
    0.15
     rencontrer
    0.14
    .Criteria
    0.14
    -lnd
    0.14
    castle
    0.14
    Insets
    0.14
    ="__
    0.14
    Act Density 0.004%

    No Known Activations