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

    Neuronpedia

    INDEX
    Explanations

    expressions of loyalty and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     světě
    -0.41
    WidgetItem
    -0.37
     convite
    -0.36
     Absicht
    -0.36
    rachtet
    -0.36
    innerHeight
    -0.35
     становника
    -0.35
     isolato
    -0.35
     katanya
    -0.35
    rrggbb
    -0.35
    POSITIVE LOGITS
     loyal
    1.84
    loyal
    1.68
     loyalty
    1.62
     faithful
    1.59
     Loyal
    1.52
     Loyalty
    1.45
    loyalty
    1.44
    faithful
    1.41
     loy
    1.37
    Loyalty
    1.34
    Act Density 0.077%

    No Known Activations