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

    Neuronpedia

    INDEX
    Explanations

    references to legal claims and financial misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    ",__
    -0.16
    بÙĪاسطة
    -0.15
    cheon
    -0.15
    å¹¹ç·ļ
    -0.15
    errupted
    -0.15
    .uml
    -0.14
    ÙģÙĪ
    -0.14
     плаÑģÑĤи
    -0.14
    ifacts
    -0.14
    POSITIVE LOGITS
     false
    0.26
     scheme
    0.23
     falsely
    0.21
     Scheme
    0.21
     allegedly
    0.21
     representations
    0.21
     kick
    0.20
     fals
    0.20
    false
    0.19
     materially
    0.19
    Act Density 0.059%

    No Known Activations