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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to processes of classification and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¾°
    -0.16
     besten
    -0.16
    724
    -0.16
    loggedin
    -0.15
    eria
    -0.15
    viso
    -0.15
    avirus
    -0.14
     ilma
    -0.14
    NSS
    -0.14
    Ñĸдом
    -0.13
    POSITIVE LOGITS
     Loot
    0.17
    ady
    0.16
     area
    0.15
    erken
    0.15
    OutOf
    0.15
     Macro
    0.14
     macro
    0.14
     aspect
    0.14
     Whereas
    0.14
     bas
    0.14
    Act Density 0.169%

    No Known Activations