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

    Neuronpedia

    INDEX
    Explanations

    military conflict and strategic maneuvers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zzleHttp
    -0.59
     GenerationType
    -0.58
    IndentedString
    -0.57
    ArgsConstructor
    -0.54
    참고
    -0.52
    <unused8>
    -0.52
    [@BOS@]
    -0.52
    <unused16>
    -0.52
    <unused14>
    -0.52
    <unused3>
    -0.52
    POSITIVE LOGITS
     victory
    0.43
     menyerang
    0.39
     menang
    0.38
     estratégico
    0.37
     unsuccessful
    0.36
     fought
    0.36
     victorious
    0.36
     defeated
    0.35
     stratégique
    0.35
     victoire
    0.35
    Act Density 0.592%

    No Known Activations