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

    Neuronpedia

    INDEX
    Explanations

    phrases that express skepticism or criticism towards societal norms

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

    criticism and complaint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.65
    ConstraintMaker
    -0.51
    arschijnlijk
    -0.49
    ukone
    -0.47
     invokingState
    -0.46
     autorytatywna
    -0.45
    vician
    -0.43
    AppMethodBeat
    -0.43
     '\\;'
    -0.41
    WireFormatLite
    -0.41
    POSITIVE LOGITS
     rant
    0.77
     critique
    0.69
     lament
    0.67
     criticizing
    0.64
     complaint
    0.63
     criticism
    0.61
     criticize
    0.58
     denuncia
    0.57
     lamented
    0.56
     critici
    0.55
    Act Density 0.075%

    No Known Activations