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

    Neuronpedia

    INDEX
    Explanations

    words referencing collective or universal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erdings
    -0.57
    ául
    -0.54
    HomeAsUpEnabled
    -0.52
    тельстве
    -0.51
    fras
    -0.49
    InjectAttribute
    -0.49
    unhofer
    -0.48
    onsored
    -0.48
    терна
    -0.48
    ngrx
    -0.47
    POSITIVE LOGITS
     all
    1.97
     ALL
    1.71
     tutte
    1.69
    All
    1.68
     All
    1.67
     todas
    1.64
    all
    1.61
    Semua
    1.59
     todos
    1.57
     tutti
    1.55
    Act Density 0.363%

    No Known Activations