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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regulation or enforcement actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸį
    -0.16
    oce
    -0.16
    .scalablytyped
    -0.15
    Ñıд
    -0.15
    ãĥ¼ãĥľ
    -0.15
    .sav
    -0.14
    rieb
    -0.14
    Ùģات
    -0.14
    agenta
    -0.14
    .Accessible
    -0.14
    POSITIVE LOGITS
    ãĤ¸
    0.16
    ersh
    0.16
    év
    0.16
    er
    0.14
    iegel
    0.14
    osing
    0.14
     CreateMap
    0.14
    fen
    0.14
    erv
    0.14
    erset
    0.14
    Act Density 0.005%

    No Known Activations