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

    Neuronpedia

    INDEX
    Explanations

    instances of bullying, racism, and discrimination

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

    experiencing suffering and mistreatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jsonwebtoken
    -0.58
     MatDialog
    -0.57
     ThemeData
    -0.57
    providedIn
    -0.55
    Autoritní
    -0.54
    出版年
    -0.53
    ]")]
    -0.52
     Himo
    -0.52
     StringTokenizer
    -0.52
    yntaxException
    -0.52
    POSITIVE LOGITS
     bullying
    0.59
    bullying
    0.54
     harassment
    0.52
     acoso
    0.49
     abuse
    0.48
     Bullying
    0.47
     violencia
    0.45
     torture
    0.43
     kekerasan
    0.41
     violência
    0.41
    Act Density 0.280%

    No Known Activations