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

    Neuronpedia

    INDEX
    Explanations

    words indicating rarity or uniqueness in experiences or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nou
    -0.14
     Samar
    -0.14
     chi
    -0.14
    fter
    -0.14
     hanging
    -0.14
    dent
    -0.13
    .detect
    -0.13
    udev
    -0.13
     '''
    -0.13
     utility
    -0.13
    POSITIVE LOGITS
    atz
    0.18
    aston
    0.17
    eln
    0.16
     danmark
    0.16
    _AST
    0.16
    emax
    0.15
    ,proto
    0.15
    à¹ģà¸Ħ
    0.15
    asting
    0.15
    iert
    0.14
    Act Density 0.376%

    No Known Activations