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

    Neuronpedia

    INDEX
    Explanations

    terms related to memory and recollection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Maur
    -0.19
     kone
    -0.15
    iang
    -0.15
    ancock
    -0.15
    freeze
    -0.15
    bout
    -0.15
    ijo
    -0.14
    IGO
    -0.14
    feit
    -0.14
    ли
    -0.14
    POSITIVE LOGITS
     instead
    0.17
    ãĥ«ãĤ¯
    0.16
    MEMORY
    0.15
     depos
    0.14
    ArgsConstructor
    0.14
     MEMORY
    0.14
    ências
    0.14
     Finish
    0.14
    createQuery
    0.14
     Memory
    0.13
    Act Density 0.086%

    No Known Activations