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

    Neuronpedia

    INDEX
    Explanations

    references to choices and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otton
    -0.16
     Bah
    -0.15
    insky
    -0.14
    ESA
    -0.14
    NX
    -0.14
    roe
    -0.14
     interven
    -0.14
    çĦ¶
    -0.14
    RC
    -0.14
    edian
    -0.14
    POSITIVE LOGITS
    isky
    0.16
    AILS
    0.16
    mani
    0.15
    gnore
    0.15
    åĭ¢
    0.15
    .scalablytyped
    0.14
     simultaneously
    0.14
    CADE
    0.14
    éļİ
    0.14
    /Library
    0.14
    Act Density 0.081%

    No Known Activations