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

    Neuronpedia

    INDEX
    Explanations

    legal and official terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and formal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.57
     alike
    -0.56
    Native
    -0.55
    rather
    -0.54
    instead
    -0.52
    *.
    -0.50
    gettable
    -0.48
    âĹ¼
    -0.48
     lesser
    -0.47
    ween
    -0.47
    POSITIVE LOGITS
     consists
    1.10
     comprises
    1.09
     consisted
    1.09
     includes
    1.01
     involves
    0.94
     lasted
    0.92
     contains
    0.91
     refers
    0.91
     revolves
    0.89
     encompasses
    0.89
    Act Density 0.486%

    No Known Activations