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

    Neuronpedia

    INDEX
    Explanations

    themes of conflict and competition

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

    conflict or competition

    np_acts-logits-general · gemini-2.0-flash

    conflict and competition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indígen
    -0.79
    <unused28>
    -0.73
    <unused8>
    -0.73
    <unused74>
    -0.73
    <unused17>
    -0.73
    [@BOS@]
    -0.73
    <unused43>
    -0.73
    <unused68>
    -0.73
    <unused52>
    -0.73
    <pad>
    -0.72
    POSITIVE LOGITS
     battle
    0.96
     battles
    0.85
     fight
    0.84
     clash
    0.81
    battle
    0.80
     Battle
    0.78
    Battle
    0.73
     battled
    0.73
    fight
    0.72
     fought
    0.72
    Act Density 0.458%

    No Known Activations