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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of being "lost."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lest
    -0.16
    вÑĸлÑĮ
    -0.15
    stad
    -0.15
    pii
    -0.15
    ÑĢок
    -0.15
    ilian
    -0.14
    lef
    -0.14
    istas
    -0.14
    ALE
    -0.14
     palms
    -0.14
    POSITIVE LOGITS
     lost
    0.26
     Lost
    0.26
    Lost
    0.23
    lost
    0.23
    _lost
    0.18
    失
    0.17
     Worlds
    0.16
     forever
    0.16
    kul
    0.16
    vg
    0.15
    Act Density 0.014%

    No Known Activations