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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating groups or collections of items

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Tema
    -0.65
    بوابة
    -0.64
     nakalista
    -0.63
     Dirichlet
    -0.57
    foe
    -0.55
    Torch
    -0.54
    usel
    -0.54
     ASC
    -0.52
    NodeList
    -0.52
     Schmidt
    -0.51
    POSITIVE LOGITS
     виправивши
    0.83
    ]<<"
    0.79
    +:+
    0.78
     BoxDecoration
    0.77
    ()]);
    0.76
    ]=-
    0.76
    tagHelperRunner
    0.71
    ftagPool
    0.69
     Rind
    0.68
     дописавши
    0.67
    Act Density 0.022%

    No Known Activations