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

    Neuronpedia

    INDEX
    Explanations

    phrases and descriptions that indicate characterization or qualities of subjects

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

    described as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtate
    -0.52
    IndentedString
    -0.49
     Infór
    -0.46
     purpoſe
    -0.44
     pourtant
    -0.42
     houſe
    -0.42
    apprendre
    -0.41
    enheim
    -0.41
     presidencia
    -0.40
     ſal
    -0.40
    POSITIVE LOGITS
     propOrder
    0.50
    awtextra
    0.49
    brigens
    0.43
    :✨
    0.43
     unique
    0.43
     is
    0.42
     considered
    0.42
     является
    0.41
    这是一
    0.41
    截至
    0.41
    Act Density 0.032%

    No Known Activations