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

    Neuronpedia

    INDEX
    Explanations

    terms associated with protective or supportive concepts, particularly in legal or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    voorbeeld
    -0.73
     OMITBAD
    -0.73
    m
    -0.73
     متعلقه
    -0.70
    oneofs
    -0.69
     Lesnar
    -0.69
     cartões
    -0.67
    XmlIgnore
    -0.67
    skjaer
    -0.67
    GEBURTSDATUM
    -0.66
    POSITIVE LOGITS
    ative
    1.33
    sive
    1.10
    ATIVE
    1.04
     sive
    1.02
     tive
    1.00
    lective
    1.00
    itive
    0.99
    IVE
    0.98
    essive
    0.97
    tive
    0.96
    Act Density 0.177%

    No Known Activations