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

    Neuronpedia

    INDEX
    Explanations

    references to specific characteristics or attributes of subjects or samples in a study

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

    those/which/whose introducing clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rob
    -0.33
     Franke
    -0.31
     OS
    -0.30
    web
    -0.30
     BR
    -0.30
     web
    -0.30
     Aufla
    -0.29
    ,
    -0.29
     со
    -0.29
     En
    -0.29
    POSITIVE LOGITS
     للاسماء
    0.92
    :✨
    0.76
    ThroughAttribute
    0.68
     dreapta
    0.67
    expandindo
    0.66
    antMatchers
    0.65
    ðsíða
    0.62
     geweſen
    0.60
     stanga
    0.60
     wikipagina
    0.60
    Act Density 0.138%

    No Known Activations