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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and symbols, particularly related to estimators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.93
     Pais
    -0.82
    lyde
    -0.76
     Pang
    -0.74
    ificantly
    -0.74
    userdetails
    -0.73
     Hoffmann
    -0.73
     Castell
    -0.73
     numberWith
    -0.73
     McGuire
    -0.73
    POSITIVE LOGITS
     hat
    2.00
    hat
    1.97
     hats
    1.92
     Hat
    1.90
    Hat
    1.80
     HAT
    1.75
    HAT
    1.57
     Hats
    1.55
    Hats
    1.47
    hats
    1.46
    Act Density 0.124%

    No Known Activations