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

    Neuronpedia

    INDEX
    Explanations

    words related to loyalty

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "loyal" and related phrases indicating loyalty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paces
    -0.70
     convol
    -0.63
     puberty
    -0.63
    scape
    -0.62
    GAME
    -0.59
     stabilization
    -0.58
     concussion
    -0.58
     skelet
    -0.58
    inventoryQuantity
    -0.57
    cloth
    -0.57
    POSITIVE LOGITS
    alty
    1.02
     allegiance
    1.00
     loyal
    0.98
     oath
    0.97
    ists
    0.95
     loyalty
    0.93
    ty
    0.93
    hip
    0.90
    ary
    0.90
     followers
    0.90
    Act Density 0.077%

    No Known Activations