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

    Neuronpedia

    INDEX
    Explanations

    references to different levels or types of floors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    جوايز
    -0.66
    espère
    -0.59
    cierge
    -0.58
     елның
    -0.58
     nonatomic
    -0.58
     Ome
    -0.58
     săptăm
    -0.57
     monographs
    -0.57
     regrets
    -0.57
     Domes
    -0.56
    POSITIVE LOGITS
     floor
    0.84
     job
    0.80
     ground
    0.77
    djangoproject
    0.64
     Floor
    0.64
     متعلقه
    0.64
     Job
    0.60
    GrantedAuthority
    0.58
     án
    0.58
    ground
    0.58
    Act Density 0.121%

    No Known Activations