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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to what one receives or experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of receiving or obtaining something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Principle
    -0.65
     annex
    -0.60
     cardinal
    -0.60
     centerpiece
    -0.57
     Family
    -0.57
     demol
    -0.56
     maiden
    -0.55
    unts
    -0.55
     modesty
    -0.54
     corrid
    -0.53
    POSITIVE LOGITS
     rid
    1.05
    DragonMagazine
    0.87
    cation
    0.80
     from
    0.79
    soever
    0.77
     rewarded
    0.77
     thrown
    0.76
    acet
    0.74
     sucked
    0.74
     stuck
    0.72
    Act Density 0.046%

    No Known Activations