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

    Neuronpedia

    INDEX
    Explanations

    Punctuation or special symbols that separate content, particularly those that may indicate sections or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steen
    -0.17
     Hath
    -0.15
    ing
    -0.15
    opia
    -0.15
     Marshall
    -0.15
    ovich
    -0.15
    Suite
    -0.15
    ÛĮÙĩ
    -0.14
    unes
    -0.14
    uster
    -0.14
    POSITIVE LOGITS
    Ĥæķ°
    0.16
    licit
    0.16
    ftware
    0.15
    anford
    0.14
    Ãłu
    0.14
    ieee
    0.14
    AZY
    0.14
    ستاÙĨÛĮ
    0.14
     Tactics
    0.14
    asse
    0.14
    Act Density 0.008%

    No Known Activations