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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation or admiration

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

    worth, awe, enjoyed, can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.83
     OMITBAD
    -0.66
     ivelany
    -0.62
    GOTREF
    -0.60
    Autoritní
    -0.59
    Παραπομπές
    -0.57
     Италијани
    -0.57
     يتيمه
    -0.57
     utafitiHapana
    -0.57
    IntoConstraints
    -0.56
    POSITIVE LOGITS
    NTP
    0.36
    Finalmente
    0.36
     🌟
    0.36
    ventura
    0.35
    存于互联网档案馆
    0.34
    、【
    0.33
     Rounds
    0.33
    gem
    0.33
     ⭐
    0.33
     Appearance
    0.32
    Act Density 0.003%

    No Known Activations