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

    Neuronpedia

    INDEX
    Explanations

    phrases concerning rules, norms, and the behavior of individuals or groups in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lichung
    -0.52
     BoxFit
    -0.52
    brainly
    -0.51
    writeFieldEnd
    -0.51
    velocityY
    -0.51
    ())){
    -0.44
    ")){
    -0.44
     noqa
    -0.44
    NgModule
    -0.43
    InSection
    -0.43
    POSITIVE LOGITS
    ViewFeatures
    0.69
     üb
    0.65
     solito
    0.64
     notoriously
    0.58
     Batteries
    0.57
     usually
    0.57
     brukar
    0.57
     customary
    0.57
     typically
    0.56
     usual
    0.55
    Act Density 0.484%

    No Known Activations