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

    Neuronpedia

    INDEX
    Explanations

    discussions of ideological conflicts and inconsistencies in beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kê
    -0.14
     brag
    -0.14
    aylor
    -0.14
    ayd
    -0.14
    .getElementsByName
    -0.14
    plen
    -0.14
     jack
    -0.14
     torch
    -0.13
     Jack
    -0.13
    atings
    -0.13
    POSITIVE LOGITS
    azes
    0.15
    lyn
    0.14
    errer
    0.14
    utor
    0.14
    endez
    0.14
    fur
    0.14
    ondo
    0.14
    ModelProperty
    0.14
    udi
    0.14
    entina
    0.14
    Act Density 0.356%

    No Known Activations