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

    Neuronpedia

    INDEX
    Explanations

    terms related to weights in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Viitteet
    -0.69
    脚注の使い方
    -0.64
    UMBIA
    -0.64
     оригіналу
    -0.63
    acherous
    -0.62
     للمعارف
    -0.62
     ―――――
    -0.61
     mør
    -0.61
    aaral
    -0.61
     DAS
    -0.60
    POSITIVE LOGITS
    jspx
    0.64
     inne
    0.63
     vela
    0.60
    NameInMap
    0.59
    tvar
    0.57
    fml
    0.57
    RequestBody
    0.55
     Nader
    0.55
    stable
    0.54
     Renoir
    0.54
    Act Density 0.185%

    No Known Activations