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

    Neuronpedia

    INDEX
    Explanations

    terms related to membership and organizational affiliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Warburton
    -0.79
     Warwick
    -0.63
     extremity
    -0.63
    jona
    -0.62
     Filters
    -0.61
     Yud
    -0.60
     Lone
    -0.59
     Rink
    -0.59
     Yew
    -0.58
    xt
    -0.58
    POSITIVE LOGITS
     membership
    1.20
    membership
    1.13
     Membership
    1.10
     MEMBERSHIP
    1.03
     registration
    1.01
    Membership
    0.98
     admission
    0.94
     enrollment
    0.92
    admission
    0.92
     Registration
    0.91
    Act Density 0.098%

    No Known Activations