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

    Neuronpedia

    INDEX
    Explanations

    phrases related to security and data protection measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç³ĸ
    -0.14
    .netbeans
    -0.14
    ÅĻiv
    -0.13
    achsen
    -0.12
    ooke
    -0.12
    _TUN
    -0.12
    afx
    -0.12
    quets
    -0.12
    quiv
    -0.11
    kening
    -0.11
    POSITIVE LOGITS
     destruction
    0.34
     shredd
    0.34
     Destruction
    0.33
     shred
    0.29
     destroy
    0.29
     Destroy
    0.28
     shredded
    0.28
     disposal
    0.28
     destroying
    0.28
     erase
    0.27
    Act Density 0.008%

    No Known Activations