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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ensuring safety and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.66
    ArgsConstructor
    -0.59
    BeginContext
    -0.57
     Wikimedijinoj
    -0.56
     BoxFit
    -0.56
    InitVars
    -0.55
     INTERESAR
    -0.55
     оригіналу
    -0.55
    BeginInit
    -0.55
     مشين
    -0.54
    POSITIVE LOGITS
     smooth
    1.27
     proper
    1.22
     optimal
    1.14
     efficient
    1.07
     optimum
    1.06
     adequate
    1.04
     effective
    1.01
     successful
    1.00
     timely
    0.98
    proper
    0.97
    Act Density 0.608%

    No Known Activations