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

    Neuronpedia

    INDEX
    Explanations

    references to articles and sources from news publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okus
    -0.17
    ius
    -0.16
    \Traits
    -0.15
    eria
    -0.14
    sted
    -0.14
    479
    -0.13
    Narrated
    -0.13
    eries
    -0.13
    enden
    -0.13
    uti
    -0.13
    POSITIVE LOGITS
     Wall
    0.44
    Wall
    0.33
     Times
    0.33
     New
    0.32
     Guardian
    0.31
     Washington
    0.31
     Associated
    0.30
    Times
    0.30
     WS
    0.28
     WALL
    0.28
    Act Density 0.267%

    No Known Activations