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

    Neuronpedia

    INDEX
    Explanations

    references to groups or collectives in different contexts

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

    pronoun + preposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.91
     متعلقه
    -0.91
     esternos
    -0.89
    }';
    -0.79
    ]--;
    -0.77
    hematical
    -0.75
    ()");
    -0.74
     />);
    -0.74
     "..\..\..\
    -0.73
    ())));
    -0.73
    POSITIVE LOGITS
     to
    0.66
     with
    0.63
     as
    0.62
     in
    0.59
     up
    0.57
     into
    0.51
     down
    0.49
     back
    0.47
     along
    0.47
     onto
    0.46
    Act Density 0.055%

    No Known Activations