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

    Neuronpedia

    INDEX
    Explanations

    relationships between entities and their interactions, particularly in the context of parental roles and individual identities in social situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onBind
    -0.72
    RegressionTest
    -0.63
    reportWebVitals
    -0.61
    adaptiveStyles
    -0.59
    Général
    -0.57
    Iacute
    -0.56
    -0.54
    '},
    -0.54
     onlyOwner
    -0.54
     متعلقه
    -0.53
    POSITIVE LOGITS
    どちら
    0.67
     referenties
    0.65
     mourut
    0.62
     partij
    0.61
    :✨
    0.60
     helft
    0.58
    どっち
    0.58
     تعدى
    0.56
     peindre
    0.55
    älfte
    0.54
    Act Density 0.780%

    No Known Activations