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

    Neuronpedia

    INDEX
    Explanations

    discussions about the subjects and their states or actions, particularly focusing on personal pronouns and references

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

    pronoun followed by modal verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    styleType
    -0.61
     незавершена
    -0.56
    Véxase
    -0.53
    Derbyniad
    -0.53
    Hentet
    -0.52
     للاسماء
    -0.52
    ########.
    -0.51
    Jeografia
    -0.51
     aDecoder
    -0.50
     invokingState
    -0.50
    POSITIVE LOGITS
     therefore
    0.45
     նաև
    0.40
     incluso
    0.40
     даже
    0.39
     sogar
    0.39
     Therefore
    0.38
     Literally
    0.37
     quindi
    0.37
     навіть
    0.36
    CloseOperation
    0.36
    Act Density 0.053%

    No Known Activations