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

    Neuronpedia

    INDEX
    Explanations

    concepts related to equality and social justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.57
     hard
    -0.52
    ilas
    -0.52
     Monte
    -0.52
    iloc
    -0.50
     very
    -0.50
     Ho
    -0.49
    asse
    -0.48
    )
    -0.48
    ITABLE
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    1.29
    ValueStyle
    1.08
    ViewFeatures
    1.00
     esternos
    0.89
     utafitiHapana
    0.88
     defaultstate
    0.84
     resourceCulture
    0.82
     pageContext
    0.80
    EndGlobalSection
    0.79
     للمعارف
    0.78
    Act Density 0.342%

    No Known Activations