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

    Neuronpedia

    INDEX
    Explanations

    instances of frameworks or systems that serve as models or templates for other processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hallmark
    -0.16
    uby
    -0.15
     Dome
    -0.15
    allis
    -0.14
    pickle
    -0.14
    multiline
    -0.14
    831
    -0.14
    Äħż
    -0.13
    pcl
    -0.13
     ded
    -0.13
    POSITIVE LOGITS
     basis
    0.45
     foundation
    0.45
     starting
    0.40
    foundation
    0.39
    basis
    0.39
     base
    0.37
     framework
    0.36
     foundations
    0.35
     Basis
    0.35
    starting
    0.34
    Act Density 0.279%

    No Known Activations