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

    Neuronpedia

    INDEX
    Explanations

    declaring or stating something as true or necessary within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "is" followed by an adverb, adjective, or preposition

    np_acts-logits-general · gemini-2.0-flash

    is followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelves
    -0.98
    ſelf
    -0.83
     myſelf
    -0.82
     ſta
    -0.78
     ſche
    -0.75
     itſelf
    -0.73
     diſt
    -0.73
     pleaſure
    -0.73
     preſent
    -0.72
     ſever
    -0.71
    POSITIVE LOGITS
    在于
    0.55
    a
    0.44
    either
    0.42
    namely
    0.39
     Factbook
    0.38
     the
    0.38
    is
    0.37
    重要的是
    0.34
    当然是
    0.34
     surla
    0.33
    Act Density 0.327%

    No Known Activations