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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recognition and acknowledgment of achievements

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

    recognition and honor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сылкі
    -0.74
    OGND
    -0.63
     '\\;'
    -0.62
    hoeddwyd
    -0.61
     linkovi
    -0.60
     informée
    -0.58
     gyhoeddwyd
    -0.54
     autorytatywna
    -0.54
     Италијани
    -0.53
    WarningLevel
    -0.53
    POSITIVE LOGITS
     recognition
    0.47
     Anerkennung
    0.40
    recognition
    0.39
     recogni
    0.38
     penghargaan
    0.36
     récompense
    0.36
     honor
    0.35
     reconhecimento
    0.33
     resultCode
    0.33
    Recognition
    0.33
    Act Density 0.009%

    No Known Activations