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

    Neuronpedia

    INDEX
    Explanations

    the presence of certain Greek letters denoting mathematical variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     battery
    -0.78
     Battery
    -0.73
    battery
    -0.69
    Battery
    -0.68
     batteries
    -0.66
    κή
    -0.56
     batterie
    -0.54
     Batteries
    -0.52
     baterías
    -0.52
    ularia
    -0.52
    POSITIVE LOGITS
    nu
    2.56
    Nu
    1.96
     Nu
    1.93
     nu
    1.84
    NU
    1.68
     NU
    1.41
    Nuke
    1.14
     ν
    1.00
    nue
    0.99
     Numa
    0.97
    Act Density 0.080%

    No Known Activations