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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe ethical considerations and the manner of doing things

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

    how something is done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nodoc
    -0.56
    ButterKnife
    -0.37
    providedIn
    -0.37
    enderror
    -0.35
    SqlParameter
    -0.35
     Roskov
    -0.35
     secador
    -0.35
     Summe
    -0.34
    aarrggbb
    -0.33
     escenas
    -0.32
    POSITIVE LOGITS
     manner
    0.69
     way
    0.68
     ways
    0.67
     manière
    0.61
    manner
    0.61
     façons
    0.60
     maniera
    0.58
    posób
    0.58
     façon
    0.57
     fashion
    0.56
    Act Density 0.101%

    No Known Activations