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

    Neuronpedia

    INDEX
    Explanations

    nouns indicating roles, professions, or identities of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aminer
    -0.17
    cient
    -0.16
     spou
    -0.16
    ctal
    -0.16
    andal
    -0.16
    rud
    -0.15
    SO
    -0.15
     thÆ°Æ¡ng
    -0.14
    byn
    -0.14
    ervo
    -0.14
    POSITIVE LOGITS
     former
    0.24
    .k
    0.23
     member
    0.20
     frequent
    0.19
     native
    0.16
     frequ
    0.16
    woke
    0.15
     fixture
    0.15
     Former
    0.15
     long
    0.15
    Act Density 0.129%

    No Known Activations