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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "lost" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lest
    -0.18
    antz
    -0.15
    Compose
    -0.15
    ãĥ³ãĥĦ
    -0.15
    /activity
    -0.15
    esModule
    -0.15
    ÑĢок
    -0.15
    llib
    -0.14
    à¹īà¸Ń
    -0.14
    rna
    -0.14
    POSITIVE LOGITS
     Lost
    0.31
     lost
    0.30
    Lost
    0.28
    lost
    0.26
    _lost
    0.20
    失
    0.17
    ering
    0.16
    oulos
    0.16
     forever
    0.16
     souls
    0.15
    Act Density 0.018%

    No Known Activations