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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to similarity and comparison within various contexts

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

    "... the same ..."

    np_acts-logits-general · gemini-2.0-flash

    identifies 'same'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    defaultProps
    -0.48
    })));
    -0.45
     себе
    -0.43
     nonUne
    -0.43
    Carriera
    -0.43
     صوتيه
    -0.42
    verwijspagina
    -0.40
     Papers
    -0.40
    woon
    -0.40
     متحده
    -0.39
    POSITIVE LOGITS
     mesmas
    0.57
     same
    0.53
     dieselben
    0.52
     mêmes
    0.51
     mismas
    0.51
     gleichen
    0.50
     dezelfde
    0.50
    same
    0.49
     mesmos
    0.49
     dieselbe
    0.49
    Act Density 0.817%

    No Known Activations