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

    Neuronpedia

    INDEX
    Explanations

    components related to failures and attributes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itti
    -0.16
    ÏĥÏĦÏģο
    -0.15
    .pref
    -0.15
    cobra
    -0.14
    stu
    -0.14
    ç±
    -0.14
    ALI
    -0.14
     bey
    -0.14
    reen
    -0.14
    ,{"
    -0.14
    POSITIVE LOGITS
    bjerg
    0.21
    .IContainer
    0.16
    ummings
    0.16
    kaar
    0.15
    hazi
    0.15
     Pie
    0.15
    agh
    0.15
    Ŀ¼
    0.15
    .scalablytyped
    0.14
    isay
    0.14
    Act Density 0.058%

    No Known Activations