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

    Neuronpedia

    INDEX
    Explanations

    terms related to characters or classes in gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pagal
    -0.46
    Kjelder
    -0.44
     astore
    -0.40
     propOrder
    -0.40
     resourceCulture
    -0.40
    NameInMap
    -0.39
     zimowa
    -0.38
    Reasonable
    -0.38
     Descub
    -0.38
     sepanjang
    -0.36
    POSITIVE LOGITS
    mancy
    0.63
     gauntlet
    0.52
    strike
    0.52
    principalColumn
    0.52
    realm
    0.51
     Manipulation
    0.50
     shard
    0.50
     shards
    0.49
     Cores
    0.49
    locke
    0.48
    Act Density 0.676%

    No Known Activations