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

    Neuronpedia

    INDEX
    Explanations

    statements expressing the importance or necessity of particular concepts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ntag
    -0.16
    .servers
    -0.16
    ëĮĢ를
    -0.15
    arity
    -0.14
    uve
    -0.14
    ngle
    -0.14
    isle
    -0.14
    emme
    -0.14
    IFORM
    -0.14
    ilter
    -0.13
    POSITIVE LOGITS
    jeta
    0.17
    kup
    0.15
    owler
    0.15
    enal
    0.14
     Known
    0.14
    anth
    0.14
    _transient
    0.14
    à¹ĩà¸Ķ
    0.13
    \.
    0.13
    assen
    0.13
    Act Density 0.072%

    No Known Activations