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

    Neuronpedia

    INDEX
    Explanations

    references to authority and power dynamics in interpersonal interactions

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

    Lady Messalina or Queen replies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    twimg
    -0.37
    RegressionTest
    -0.34
     travers
    -0.33
     useAuth
    -0.32
     Tij
    -0.32
     CRUZ
    -0.31
    static
    -0.31
     rails
    -0.31
    @[+][
    -0.31
    writeTo
    -0.31
    POSITIVE LOGITS
    :✨
    0.63
     hurriedly
    0.57
    хьтан
    0.55
     trembled
    0.52
    obviously
    0.51
     незавершена
    0.51
     obviously
    0.51
     panicked
    0.50
     nervousness
    0.49
     nervously
    0.49
    Act Density 0.017%

    No Known Activations