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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grav
    -0.15
     cons
    -0.15
    endor
    -0.14
    æª
    -0.14
    avanaugh
    -0.14
     wnd
    -0.14
     Stan
    -0.14
    812
    -0.14
    istra
    -0.14
    81
    -0.13
    POSITIVE LOGITS
    hua
    0.15
    ORM
    0.15
     absolut
    0.15
     préc
    0.14
    CADE
    0.14
    elter
    0.14
     Rena
    0.14
     absol
    0.14
    AIT
    0.14
    renc
    0.14
    Act Density 0.006%

    No Known Activations