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

    Neuronpedia

    INDEX
    Explanations

    references to conflicts or confrontations involving significant stakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conflict or disagreement

    np_acts-logits-general · gemini-2.0-flash

    battles and conflicts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.76
     Picchu
    -0.65
     réussite
    -0.57
     secours
    -0.53
     positivo
    -0.52
     positif
    -0.51
     dAtA
    -0.50
     malheur
    -0.50
     setTotal
    -0.49
     xinh
    -0.49
    POSITIVE LOGITS
     battle
    1.94
     battles
    1.78
     conflict
    1.76
     fight
    1.74
     dispute
    1.65
    battle
    1.61
     rivalry
    1.60
     tuss
    1.59
     clash
    1.59
     fights
    1.56
    Act Density 0.584%

    No Known Activations