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

    Neuronpedia

    INDEX
    Explanations

    terms related to computational systems and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scal
    -0.18
    èĮĤ
    -0.17
     Scalars
    -0.15
     Greenwich
    -0.15
     va
    -0.14
    Pragma
    -0.14
     Paul
    -0.14
    ãĥIJãĤ¹
    -0.14
    ¥
    -0.14
     parach
    -0.14
    POSITIVE LOGITS
     alphabet
    0.20
     kle
    0.19
    alphabet
    0.18
     transitional
    0.17
    States
    0.17
     Alphabet
    0.17
     States
    0.16
     CHARSET
    0.16
    -transition
    0.16
     Transition
    0.16
    Act Density 0.016%

    No Known Activations