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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to formulas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.63
    main
    -0.57
     main
    -0.56
     parseFrom
    -0.56
    RunWith
    -0.56
    Cou
    -0.54
    CopyWith
    -0.53
    čnih
    -0.50
    üyada
    -0.49
     principali
    -0.49
    POSITIVE LOGITS
    hdashline
    0.76
    Tikang
    0.67
    nologue
    0.61
     متعلقه
    0.60
    genstein
    0.60
     poudre
    0.60
    casio
    0.59
    henswürdigkeiten
    0.58
    ainville
    0.58
    ])))
    0.58
    Act Density 0.011%

    No Known Activations