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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to military or historical events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ·ãĥ£
    -0.78
    ãĥīãĥ©ãĤ´ãĥ³
    -0.74
     Âł Âł Âł Âł
    -0.74
    CEPT
    -0.73
    terday
    -0.72
    ãĥĨãĤ£
    -0.69
    ãĥ´
    -0.68
    çīĪ
    -0.66
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.65
    ãĤ´ãĥ³
    -0.65
    POSITIVE LOGITS
    leground
    1.11
    alions
    1.08
    lest
    1.02
    erers
    0.94
    lers
    0.90
    arella
    0.86
    blers
    0.82
    ings
    0.82
    eenth
    0.81
    alore
    0.80
    Act Density 0.035%

    No Known Activations