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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or personal pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æk
    -0.17
    nun
    -0.17
    erva
    -0.15
    eck
    -0.15
    smarty
    -0.15
    ormsg
    -0.15
    erland
    -0.14
    ecko
    -0.14
    ekk
    -0.14
    ataka
    -0.14
    POSITIVE LOGITS
    u
    0.17
    ensus
    0.16
     Nah
    0.15
     Duch
    0.15
     cont
    0.15
     Ez
    0.14
     Le
    0.14
    -picture
    0.14
    inst
    0.14
    zl
    0.14
    Act Density 0.005%

    No Known Activations