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

    Neuronpedia

    INDEX
    Explanations

    titles of nobility or knighthood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.86
     APL
    -0.82
    ()));
    -0.78
    ()));
    -0.77
    "));
    -0.76
    ()]);
    -0.73
    "]);
    -0.72
     Lovato
    -0.72
    ")));
    -0.72
     Alpen
    -0.71
    POSITIVE LOGITS
     Sir
    1.95
    Sir
    1.69
     Lady
    1.60
     SIR
    1.55
     LADY
    1.55
     sir
    1.44
    SIR
    1.42
    Lady
    1.41
    LADY
    1.36
     lady
    1.34
    Act Density 0.087%

    No Known Activations