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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Britons
    -0.69
     Crusade
    -0.67
     Ukrain
    -0.64
    Reviewer
    -0.62
     conflic
    -0.61
     Pill
    -0.60
    gow
    -0.59
     Grail
    -0.59
    ModLoader
    -0.58
     Scots
    -0.58
    POSITIVE LOGITS
    ;
    1.30
    .;
    1.27
     ;
    0.90
    ;"
    0.90
    %;
    0.83
    ';
    0.79
    ();
    0.76
    ];
    0.74
    .
    0.73
    ;;
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.