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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awareness or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    modal verbs and following clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.56
    parsedMessage
    -0.54
    DebuggerNonUser
    -0.53
    RenderAtEndOf
    -0.53
     Himo
    -0.52
    ContentAsync
    -0.50
     EconPapers
    -0.49
    sidemargin
    -0.47
    basicConfig
    -0.47
    principalColumn
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.42
     Wahrheit
    0.39
     Donnelly
    0.36
     Sünden
    0.35
     Huber
    0.35
     these
    0.35
     ingenting
    0.35
    なお
    0.35
     picioare
    0.34
     justru
    0.34
    Act Density 0.040%

    No Known Activations