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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to legal arguments and reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.15
     Peters
    -0.15
    rani
    -0.15
    aight
    -0.14
     Lump
    -0.14
    enk
    -0.14
     bell
    -0.14
    nown
    -0.14
    aty
    -0.14
     perpet
    -0.14
    POSITIVE LOGITS
     stretch
    0.22
     Stretch
    0.21
     stretched
    0.20
    Stretch
    0.20
    stretch
    0.19
     stretching
    0.19
     stret
    0.19
     stretches
    0.18
    çij
    0.17
     nit
    0.16
    Act Density 0.097%

    No Known Activations