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

    Neuronpedia

    INDEX
    Explanations

    quantifiable statistics or numerical data related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     remainder
    -0.31
     rest
    -0.20
     remaining
    -0.17
    remainder
    -0.17
     Happy
    -0.16
     happy
    -0.16
     happier
    -0.16
     Remaining
    -0.15
    _MALLOC
    -0.15
     predomin
    -0.15
    POSITIVE LOGITS
     most
    0.46
     ê°Ģìŀ¥
    0.36
     MOST
    0.36
    most
    0.35
    æľĢ
    0.34
    -most
    0.34
     least
    0.32
    ãĤĤãģ£ãģ¨
    0.32
     सबस
    0.31
    _most
    0.31
    Act Density 0.246%

    No Known Activations