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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the support or compatibility of various features or technologies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the functionality and compatibility of technology or devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conserv
    -0.83
    quin
    -0.83
    isode
    -0.80
    chel
    -0.79
    ila
    -0.79
    flies
    -0.77
    wage
    -0.76
    urus
    -0.75
    urt
    -0.75
    bush
    -0.74
    POSITIVE LOGITS
     DirectX
    1.01
     IPv
    1.00
     Unicode
    0.93
     UTF
    0.91
     integer
    0.88
     HTTPS
    0.88
     JSON
    0.88
     languages
    0.86
     iPhones
    0.86
     OpenGL
    0.85
    Act Density 0.147%

    No Known Activations