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

    Neuronpedia

    INDEX
    Explanations

    architectural features and historical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enta
    -0.14
     Jung
    -0.14
    ingu
    -0.14
    ordan
    -0.14
     Durant
    -0.13
    gcc
    -0.13
     analyzes
    -0.13
    adele
    -0.13
     redund
    -0.13
    ALA
    -0.13
    POSITIVE LOGITS
     tumble
    0.15
     survive
    0.15
     survival
    0.15
     keyed
    0.15
     survives
    0.15
    нова
    0.15
    assage
    0.14
    ãĢĤ↵↵↵↵↵↵
    0.14
    uido
    0.14
    opal
    0.14
    Act Density 0.003%

    No Known Activations