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

    Neuronpedia

    INDEX
    Explanations

    elements related to community values and guiding principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    compressed
    -0.14
    elyn
    -0.14
    oug
    -0.13
    oucher
    -0.13
    .jetbrains
    -0.13
    _clock
    -0.13
     bordered
    -0.13
    oux
    -0.13
    stroy
    -0.13
    .mixin
    -0.13
    POSITIVE LOGITS
     inform
    0.50
     informs
    0.47
    inform
    0.45
     informed
    0.44
     informing
    0.44
     Inform
    0.43
    Inform
    0.41
     shape
    0.35
     shapes
    0.32
     under
    0.32
    Act Density 0.241%

    No Known Activations