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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and their correct usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IX
    -0.17
    hip
    -0.16
    elic
    -0.15
    olor
    -0.15
    ey
    -0.15
    arine
    -0.15
    istics
    -0.14
    /or
    -0.14
     hip
    -0.14
    OfType
    -0.14
    POSITIVE LOGITS
    fully
    0.24
    proper
    0.19
    ly
    0.19
     Proper
    0.18
     functioning
    0.18
    ment
    0.17
     nouns
    0.17
    mente
    0.16
    bred
    0.16
    -function
    0.16
    Act Density 0.023%

    No Known Activations