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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and courtroom contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PFN
    -0.15
    Native
    -0.15
    ique
    -0.14
    probe
    -0.14
     judgement
    -0.14
    åīĽ
    -0.14
    ongo
    -0.14
     Native
    -0.14
     [âĢ¦]
    -0.14
    Ensure
    -0.14
    POSITIVE LOGITS
     embraced
    0.17
     chan
    0.16
     infer
    0.15
     sustaining
    0.15
     upon
    0.15
     iv
    0.15
     Upon
    0.15
     Porto
    0.15
     criticised
    0.15
     sustain
    0.15
    Act Density 0.119%

    No Known Activations