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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating challenges and limitations

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

    despite preceding contrasting information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.50
    Jereo
    -0.47
    хьтан
    -0.46
    AccessFile
    -0.44
    ьаж
    -0.43
    Personensuche
    -0.42
    ToReturn
    -0.42
    FieldBuilder
    -0.41
    queryInterface
    -0.40
    ArgsConstructor
    -0.39
    POSITIVE LOGITS
    Despite
    0.67
     Despite
    0.66
     Malgré
    0.60
    ostante
    0.52
     despite
    0.52
    尽管
    0.51
    despite
    0.51
     nonostante
    0.49
     Notwithstanding
    0.47
    Though
    0.47
    Act Density 0.032%

    No Known Activations