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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to calculus and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    processable
    -0.15
    895
    -0.14
    ller
    -0.14
    ãģĹãĤĩ
    -0.14
    imary
    -0.14
    gebra
    -0.14
    lege
    -0.14
    imuth
    -0.14
    PDO
    -0.14
    rijk
    -0.13
    POSITIVE LOGITS
     Dear
    0.15
     ActionTypes
    0.15
     Zam
    0.14
    1
    0.14
     others
    0.14
     ============================================================================↵
    0.14
     actionTypes
    0.14
    enburg
    0.14
    erman
    0.13
    237
    0.13
    Act Density 0.208%

    No Known Activations