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

    Neuronpedia

    INDEX
    Explanations

    references to physical objects or actions that can be touched or manipulated

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to various themes or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascal
    -0.61
    anchester
    -0.59
    andem
    -0.59
    enza
    -0.59
    ilk
    -0.58
    reek
    -0.58
    Hay
    -0.56
    roma
    -0.54
    omez
    -0.54
    ahon
    -0.53
    POSITIVE LOGITS
    usercontent
    0.55
     reperto
    0.54
     experien
    0.54
     exhib
    0.54
    ãĤ¼ãĤ¦ãĤ¹
    0.54
    Materials
    0.54
    naires
    0.53
    dayName
    0.53
    EStream
    0.52
     externalToEVAOnly
    0.51
    Act Density 0.621%

    No Known Activations