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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and components in a code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.61
     "
    -0.54
     indeed
    -0.52
     fore
    -0.51
     em
    -0.51
     also
    -0.49
    try
    -0.48
    hver
    -0.47
     not
    -0.47
    (
    -0.47
    POSITIVE LOGITS
     propOrder
    1.29
    AccessorTable
    1.18
     المعيارى
    1.02
    UnknownFieldSet
    1.00
     esternos
    0.98
    protoimpl
    0.95
     MonoBehaviour
    0.95
     snippetHide
    0.89
     createState
    0.88
    argout
    0.87
    Act Density 0.009%

    No Known Activations