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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific formal document structure or markers, such as headers or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     histoires
    -0.56
     concernant
    -0.55
    habitude
    -0.55
    ابعة
    -0.52
    BeginContext
    -0.52
     magát
    -0.50
    orologio
    -0.49
     étages
    -0.49
    Atoi
    -0.49
     tiroirs
    -0.49
    POSITIVE LOGITS
     environments
    0.60
    SharedDtor
    0.53
     дописавши
    0.53
    astéroïdes
    0.52
     errands
    0.52
     Agre
    0.52
     Mev
    0.51
     protoimpl
    0.51
    Autoritní
    0.51
    Portail
    0.50
    Act Density 0.198%

    No Known Activations