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

    Neuronpedia

    INDEX
    Explanations

    references to ideas of control and dominance over existence or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.54
    MigrationBuilder
    -0.49
     nahilalakip
    -0.48
    astify
    -0.47
    PMailer
    -0.46
    complexContent
    -0.44
    Искәрмәләр
    -0.43
     يتيمه
    -0.43
    发表于
    -0.42
    ⤒
    -0.42
    POSITIVE LOGITS
     everything
    0.67
    一切
    0.63
    Everything
    0.62
    everything
    0.61
     Everything
    0.60
    VYMaps
    0.58
     segala
    0.57
    的一切
    0.55
     mọi
    0.55
     EVERYTHING
    0.52
    Act Density 0.235%

    No Known Activations