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

    Neuronpedia

    INDEX
    Explanations

    contextual connections and relationships between various nouns and actions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARAM
    -0.15
    acre
    -0.14
    IPS
    -0.14
     substitutions
    -0.14
    tar
    -0.14
    ạm
    -0.14
    496
    -0.14
    ιÏĥμ
    -0.14
    ALA
    -0.14
     personally
    -0.13
    POSITIVE LOGITS
     different
    0.18
    ä¸įåIJĮçļĦ
    0.18
     special
    0.17
    vary
    0.16
    different
    0.16
    ifferent
    0.16
     varying
    0.16
    Different
    0.15
    ä¸įåIJĮ
    0.15
    AZY
    0.15
    Act Density 0.004%

    No Known Activations