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

    Neuronpedia

    INDEX
    Explanations

    references to various types of monsters and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.91
    ories
    -0.84
     Seym
    -0.76
    dated
    -0.74
    ynski
    -0.73
    atories
    -0.72
    choes
    -0.70
    rontal
    -0.70
    issance
    -0.69
    artisan
    -0.68
    POSITIVE LOGITS
     monsters
    0.91
     monster
    0.84
     beasts
    0.82
     wre
    0.80
     Fenrir
    0.77
     hunter
    0.77
     bite
    0.76
     vomit
    0.75
     Reborn
    0.74
     Monstrous
    0.74
    Act Density 0.009%

    No Known Activations