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

    Neuronpedia

    INDEX
    Explanations

    the term "useless" and related expressions critiquing effectiveness or value

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

    useless or without purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     okreś
    -0.43
     Administrativna
    -0.40
    Convey
    -0.39
    jména
    -0.39
     Ronan
    -0.38
     تعدى
    -0.38
    gså
    -0.38
     Berikut
    -0.38
     @"/
    -0.37
    Gön
    -0.37
    POSITIVE LOGITS
     useless
    1.95
    useless
    1.85
    Useless
    1.62
     worthless
    1.27
     inútil
    1.23
     inutile
    1.05
     pointless
    0.99
    seless
    0.95
     inuti
    0.92
     unusable
    0.86
    Act Density 0.006%

    No Known Activations