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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to blog content and user engagement features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _splits
    -0.15
    746
    -0.15
     bark
    -0.15
     withStyles
    -0.15
    373
    -0.14
     cup
    -0.14
    ropri
    -0.14
    -BEGIN
    -0.14
    LocalizedString
    -0.14
     gent
    -0.14
    POSITIVE LOGITS
    olem
    0.15
    serv
    0.15
    ustr
    0.15
     Serv
    0.15
     seins
    0.15
    edik
    0.14
     Reverse
    0.14
    uo
    0.14
    eki
    0.14
     Classe
    0.14
    Act Density 0.070%

    No Known Activations