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

    Neuronpedia

    INDEX
    Explanations

    terms related to admission and inclusivity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OrBuilder
    -0.72
    XmlRootElement
    -0.66
     rospy
    -0.63
     GaAs
    -0.63
    könyv
    -0.63
     Berikut
    -0.62
    Berikut
    -0.61
     fallecido
    -0.60
    cerned
    -0.59
     Chwiliwch
    -0.58
    POSITIVE LOGITS
     Inclusion
    1.02
    inclusion
    1.01
     rejection
    0.99
     inclusion
    0.96
     Rejection
    0.94
     Exclusion
    0.94
     Deposit
    0.94
     exclusion
    0.92
     admission
    0.91
     Deposits
    0.90
    Act Density 0.155%

    No Known Activations