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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to time and memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TRL
    -0.14
     кад
    -0.14
    μον
    -0.14
    оÑİ
    -0.14
     Baths
    -0.14
    zek
    -0.13
    icular
    -0.13
    ady
    -0.13
    WER
    -0.13
    .Persistent
    -0.13
    POSITIVE LOGITS
     Ages
    0.19
    ndo
    0.16
     victory
    0.15
     truth
    0.15
     ages
    0.15
     defeat
    0.15
     Truth
    0.14
    eri
    0.14
    .apps
    0.14
     death
    0.14
    Act Density 0.172%

    No Known Activations