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

    Neuronpedia

    INDEX
    Explanations

    names and titles related to authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lacak
    -0.15
    éł
    -0.14
    gars
    -0.14
    ênh
    -0.14
    agu
    -0.13
    .fig
    -0.13
    enden
    -0.13
    PTR
    -0.12
    ksam
    -0.12
    .btnAdd
    -0.12
    POSITIVE LOGITS
    íĥĿ
    0.14
    TK
    0.13
    -fontawesome
    0.13
    μιο
    0.13
     táºŃn
    0.13
    137
    0.12
    290
    0.12
    .ArgumentParser
    0.12
     Geological
    0.12
    267
    0.12
    Act Density 0.136%

    No Known Activations