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

    Neuronpedia

    INDEX
    Explanations

    terms related to harassment and bullying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.88
     StatefulWidget
    -0.83
    AddTagHelper
    -0.82
    Chham
    -0.77
    ValueStyle
    -0.73
    =$?
    -0.71
    BuilderFactory
    -0.71
     виправивши
    -0.71
    原始内容存档于
    -0.71
    WebVitals
    -0.70
    POSITIVE LOGITS
     bullying
    1.05
     bullied
    1.03
     harassment
    0.99
     persecution
    0.98
     bully
    0.95
     persecuted
    0.93
     persec
    0.93
     acoso
    0.91
     harassed
    0.85
     Bullying
    0.84
    Act Density 0.716%

    No Known Activations