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

    Neuronpedia

    INDEX
    Explanations

    references to group identity or collective experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ation
    -0.68
     Paar
    -0.67
     Thon
    -0.63
    ALY
    -0.63
    WithIOException
    -0.60
     residence
    -0.59
     Ath
    -0.59
     pathlib
    -0.59
    ter
    -0.58
     صفحۀ
    -0.58
    POSITIVE LOGITS
    We
    1.26
     We
    1.21
     we
    1.16
    we
    1.12
     weevil
    1.06
     Weinstein
    1.05
     Paglinawan
    0.99
     WE
    0.95
    ]))
    0.91
     vostri
    0.89
    Act Density 0.212%

    No Known Activations