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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing policy decisions or legal proceedings related to individual rights and government actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     duele
    -0.70
    Personendaten
    -0.70
     fermés
    -0.70
    MessageTagHelper
    -0.69
     Мексичка
    -0.68
    ISupport
    -0.67
    Бахар
    -0.66
     <>",
    -0.65
     AssemblyCulture
    -0.64
    principalColumn
    -0.63
    POSITIVE LOGITS
    ParallelGroup
    0.47
     cr
    0.46
    ด
    0.44
     stol
    0.43
     Bond
    0.42
    i
    0.42
    zen
    0.41
    lfs
    0.41
     protoimpl
    0.41
     uts
    0.40
    Act Density 0.156%

    No Known Activations