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

    Neuronpedia

    INDEX
    Explanations

    specific references to warranty information and disclaimers in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -0.49
     sur
    -0.48
    ParallelGroup
    -0.45
    relser
    -0.44
    newArrayList
    -0.44
    NOPQRST
    -0.44
     M
    -0.43
     ins
    -0.43
     espal
    -0.42
     railways
    -0.40
    POSITIVE LOGITS
    :✨
    0.77
     themſelves
    0.74
     itſelf
    0.71
     ſeveral
    0.70
    rungsseite
    0.70
     Majefty
    0.69
     myſelf
    0.69
     therein
    0.69
    ſelves
    0.68
     greateſt
    0.68
    Act Density 0.840%

    No Known Activations