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

    Neuronpedia

    INDEX
    Explanations

    instances of strong emphasis or key points in the text

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

    conjunctions and relative pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "])
    -0.63
     ―――――
    -0.60
    SharedDtor
    -0.60
     disambiguazione
    -0.60
    "}}>
    -0.57
    )))));
    -0.57
    }))
    -0.57
    ")));
    -0.57
    "))
    -0.57
     }}">
    -0.56
    POSITIVE LOGITS
     thru
    0.45
     cuya
    0.45
     cuyo
    0.44
     cuyas
    0.43
     daß
    0.42
     whose
    0.41
     cuyos
    0.40
     hence
    0.39
     therefore
    0.38
     cuarent
    0.36
    Act Density 0.065%

    No Known Activations