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

    Neuronpedia

    INDEX
    Explanations

    specific threats or coercive language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lawsuits
    -0.17
    _FT
    -0.17
    ̣
    -0.16
    ouro
    -0.15
    ÏĩÏİ
    -0.15
     Uncomment
    -0.14
     sue
    -0.14
    idon
    -0.14
    å¯
    -0.14
    erm
    -0.14
    POSITIVE LOGITS
     officers
    0.19
     offending
    0.17
     officer
    0.16
     breaches
    0.16
     Officers
    0.16
     sentence
    0.15
     breached
    0.15
     Mr
    0.15
    Mr
    0.14
     matters
    0.14
    Act Density 0.018%

    No Known Activations