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

    Neuronpedia

    INDEX
    Explanations

    terms related to accusations and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BaseContext
    -0.16
    íļ¨
    -0.15
    ylko
    -0.15
     Hakk
    -0.15
    _strike
    -0.15
    'gc
    -0.14
    amedi
    -0.14
    antity
    -0.14
    داد
    -0.14
     Thief
    -0.14
    POSITIVE LOGITS
     practices
    0.19
     systematic
    0.18
     Practices
    0.18
    åŃĺåľ¨
    0.17
     mem
    0.17
     possibly
    0.16
     secret
    0.16
     documented
    0.15
     doc
    0.15
     prefer
    0.15
    Act Density 0.336%

    No Known Activations