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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing a basis or foundation for arguments, ideas, or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that serve as a basis or foundation for various concepts or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bil
    -0.73
    cz
    -0.72
    chenko
    -0.70
    mort
    -0.69
    loo
    -0.69
    eps
    -0.68
    aqu
    -0.67
    oshenko
    -0.67
    kai
    -0.67
    mare
    -0.67
    POSITIVE LOGITS
    geries
    0.98
    bidden
    0.96
    gery
    0.94
     determining
    0.90
     instance
    0.85
     constructing
    0.83
    wards
    0.76
     example
    0.75
    gotten
    0.74
     establishing
    0.73
    Act Density 0.115%

    No Known Activations