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

    Neuronpedia

    INDEX
    Explanations

    phrases related to design and craftsmanship

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.80
    
    -0.69
    ValueGenerated
    -0.69
    /**
    -0.60
    vec
    -0.60
    Kontrola
    -0.60
    ⓧ
    -0.59
    EndProject
    -0.59
    CopyWith
    -0.58
    lateinit
    -0.57
    POSITIVE LOGITS
     Mémoires
    1.28
     Am
    1.27
     Traité
    1.27
     reluct
    1.17
     Amé
    1.16
    Am
    1.15
     maneu
    1.15
     Chinois
    1.14
     disreg
    1.13
     quoique
    1.13
    Act Density 0.210%

    No Known Activations