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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference legal standards and procedural language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.79
     विश्वसनीयता
    -0.74
     Theſe
    -0.74
    expandindo
    -0.73
    ArgsConstructor
    -0.72
    ſelf
    -0.72
     againſt
    -0.72
     crdi
    -0.72
     itſelf
    -0.71
     becauſe
    -0.70
    POSITIVE LOGITS
     terme
    0.48
     term
    0.45
     término
    0.44
    と呼ばれる
    0.42
     referred
    0.42
     said
    0.42
    "
    0.40
     
    0.40
     say
    0.40
     in
    0.39
    Act Density 0.514%

    No Known Activations