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

    Neuronpedia

    INDEX
    Explanations

    legal and procedural language related to regulations and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     greateſt
    -1.15
     Majefty
    -1.11
    ſelf
    -1.08
     iſt
    -1.08
    ſelves
    -1.08
     ſtate
    -1.05
     houſe
    -1.03
     Jefus
    -1.02
     ſta
    -1.02
     Diſ
    -1.00
    POSITIVE LOGITS
     to
    0.65
     in
    0.63
     em
    0.61
     for
    0.59
     a
    0.56
     the
    0.53
     nos
    0.52
    ,
    0.52
     en
    0.52
     d
    0.52
    Act Density 0.152%

    No Known Activations