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

    Neuronpedia

    INDEX
    Explanations

    the concept of uniqueness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mors
    -0.68
    FieldDescriptor
    -0.66
    стма
    -0.66
     censura
    -0.65
    dymyr
    -0.61
    Bbb
    -0.60
     fós
    -0.59
    </em>
    -0.58
    <code>
    -0.58
    shi
    -0.58
    POSITIVE LOGITS
     UNIQUE
    1.11
    UniqueId
    1.09
    UNIQUE
    1.08
     uniqu
    1.07
     uniques
    1.04
    unique
    0.99
     unique
    0.96
     Unique
    0.96
    Unique
    0.92
     unik
    0.91
    Act Density 0.071%

    No Known Activations