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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize inclusivity or collective involvement

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

    with all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ținut
    -0.46
     kasarigan
    -0.45
     ​​
    -0.45
     giacca
    -0.44
     juuri
    -0.44
     jugado
    -0.43
    fekt
    -0.42
     separado
    -0.42
    Törté
    -0.42
    verwijspagina
    -0.41
    POSITIVE LOGITS
    with
    0.64
     WITH
    0.60
     With
    0.59
    With
    0.59
    WITH
    0.56
     with
    0.50
     therewith
    0.47
     Avec
    0.47
     avec
    0.46
     با
    0.46
    Act Density 0.009%

    No Known Activations