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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or realization

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

    the word Oh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cactus
    -0.47
     SMG
    -0.45
    matite
    -0.44
     HasFactory
    -0.43
     BDS
    -0.43
     Malin
    -0.43
     PFA
    -0.42
     CCL
    -0.42
     Tartar
    -0.42
    able
    -0.41
    POSITIVE LOGITS
     Oh
    0.97
    Oh
    0.94
     oh
    0.79
     OH
    0.73
    GEBURTSDATUM
    0.65
    oh
    0.65
     gouver
    0.63
     المعيارى
    0.62
     Ohl
    0.59
     Chriſt
    0.58
    Act Density 0.009%

    No Known Activations