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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific street names

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Le" and its associated phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.89
    ividual
    -0.84
    etheless
    -0.79
    ãĥ¼ãĥĨ
    -0.74
    ãģĨ
    -0.72
    aneers
    -0.68
     CPC
    -0.66
    acca
    -0.66
     Concepts
    -0.65
    swing
    -0.64
    POSITIVE LOGITS
    isure
    1.31
    agues
    1.12
    lean
    1.06
    ukemia
    1.05
    opard
    1.05
    aky
    0.99
    icester
    0.98
    vered
    0.96
    aping
    0.96
    aching
    0.93
    Act Density 0.027%

    No Known Activations