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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and terms related to organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kul
    -0.18
     Svens
    -0.16
    enville
    -0.16
    858
    -0.15
    klass
    -0.15
    械
    -0.14
    fault
    -0.14
    láš
    -0.14
    avers
    -0.13
    amer
    -0.13
    POSITIVE LOGITS
    ogue
    0.18
    e
    0.17
    è¶
    0.17
    eros
    0.17
    UNCH
    0.16
    agg
    0.16
    inen
    0.15
    hattan
    0.15
    rat
    0.14
    svp
    0.14
    Act Density 0.023%

    No Known Activations