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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusion or modification in a list or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InstanceState
    -0.95
    RenderAtEndOf
    -0.81
    IsContent
    -0.73
    ymce
    -0.66
     تانيه
    -0.64
    __":
    -0.59
    BuildContext
    -0.59
    ismus
    -0.57
    TestTools
    -0.57
     paraphrase
    -0.56
    POSITIVE LOGITS
     incluem
    0.64
     betweenstory
    0.61
     includes
    0.56
     include
    0.56
    __(/*!
    0.56
    includes
    0.53
     nakalista
    0.51
    tvguidetime
    0.51
     inclui
    0.50
    增添
    0.49
    Act Density 0.706%

    No Known Activations