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

    Neuronpedia

    INDEX
    Explanations

    references to battles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    --
    -0.90
     Réponses
    -0.79
    ształ
    -0.75
    ITHUB
    -0.72
     firebaseConfig
    -0.72
    gebob
    -0.71
    ffine
    -0.71
    ++
    -0.70
    Cyfarwyddwr
    -0.69
    ]))
    -0.69
    POSITIVE LOGITS
     BATTLE
    0.99
     Battle
    0.98
    BATTLE
    0.93
     battle
    0.92
    battle
    0.88
     Katzen
    0.86
     Battles
    0.86
    Battle
    0.85
     battles
    0.82
    atimes
    0.80
    Act Density 0.008%

    No Known Activations