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

    Neuronpedia

    INDEX
    Explanations

    phrases related to promotions and limited-time offers

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

    "limited" or scarcity

    np_acts-logits-general · gemini-2.0-flash

    limited or finite offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.97
    ContentAlignment
    -0.78
    thâu
    -0.72
    ंदीखरीदारी
    -0.68
     esternos
    -0.67
    :+:
    -0.63
     estekak
    -0.62
     mergeFrom
    -0.61
     [*]
    -0.61
    таратура
    -0.60
    POSITIVE LOGITS
     limited
    0.98
    limited
    0.92
     Limited
    0.87
    Limited
    0.87
     LIMITED
    0.85
    LIMITED
    0.82
     terbatas
    0.71
     finite
    0.68
     limitado
    0.67
    Hurry
    0.67
    Act Density 0.172%

    No Known Activations