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

    Neuronpedia

    INDEX
    Explanations

    references to legal and governmental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aho
    -0.20
     summers
    -0.17
     pist
    -0.15
    igmat
    -0.15
    olg
    -0.15
    اÙģر
    -0.14
     winters
    -0.14
    udem
    -0.14
    andler
    -0.14
     Kolkata
    -0.14
    POSITIVE LOGITS
     Malaysia
    0.45
     Malaysian
    0.45
     Malays
    0.42
     Kuala
    0.40
     malaysia
    0.36
     RM
    0.32
     Malay
    0.32
    Mal
    0.31
     Joh
    0.29
    RM
    0.28
    Act Density 0.158%

    No Known Activations