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

    Neuronpedia

    INDEX
    Explanations

    references to specific organizations and entities

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

    specific names, categories, or identifiers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.47
    发表于
    -0.46
     Briefly
    -0.43
     Celui
    -0.42
    Bates
    -0.40
     estekak
    -0.39
     impos
    -0.39
    ázaro
    -0.37
     يتيمه
    -0.37
    gridx
    -0.37
    POSITIVE LOGITS
    expandindo
    0.60
    లు
    0.59
     క
    0.59
     అ
    0.59
    జ
    0.59
    బ
    0.58
     మీ
    0.58
    మూ
    0.58
    మ
    0.57
    ప
    0.57
    Act Density 0.091%

    No Known Activations