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

    Neuronpedia

    INDEX
    Explanations

    indications of hypothesized or suspected information

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.52
     CWE
    -0.49
     Peak
    -0.46
    Peak
    -0.46
    SaveChanges
    -0.46
    acc
    -0.46
    gitte
    -0.45
     caldo
    -0.45
    чем
    -0.43
    țul
    -0.43
    POSITIVE LOGITS
     hypothe
    0.83
     presidency
    0.82
     Presidency
    0.77
     TMPro
    0.77
    ChildScrollView
    0.75
     MCP
    0.72
    DebuggerStep
    0.71
     Gle
    0.69
    abestanden
    0.68
    ConstraintMaker
    0.68
    Act Density 0.012%

    No Known Activations