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

    Neuronpedia

    INDEX
    Explanations

    reference markers and citations in academic texts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Sosten
    -0.54
     soldati
    -0.50
    Assignable
    -0.49
     swit
    -0.48
     costumi
    -0.48
    ริ
    -0.48
     katkıda
    -0.47
     misericordia
    -0.47
     quelquefois
    -0.47
     majeurs
    -0.47
    POSITIVE LOGITS
    ConstraintMaker
    0.86
     kasarigan
    0.82
    WriteTagHelper
    0.79
     utafitiHapana
    0.77
     snippetHide
    0.75
    Personendaten
    0.73
    AddTagHelper
    0.68
    CppCodeGen
    0.66
     استنادى
    0.64
    Enllaces
    0.63
    Act Density 0.042%

    No Known Activations