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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "rem" and its variations, indicating a focus on themes of remembrance or memory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergy
    -0.16
    ernal
    -0.15
    rey
    -0.15
     McGr
    -0.14
     neat
    -0.14
    ematics
    -0.14
     Mae
    -0.14
    bris
    -0.14
    iously
    -0.14
    uzzle
    -0.14
    POSITIVE LOGITS
    /rem
    0.20
    perature
    0.19
    nants
    0.18
    rive
    0.18
     Rem
    0.17
    aldi
    0.17
     rem
    0.17
    rem
    0.17
    ovable
    0.17
    veis
    0.16
    Act Density 0.022%

    No Known Activations