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

    Neuronpedia

    INDEX
    Explanations

    references to perspectives, viewpoints, and interpretations in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.75
    
    -0.59
     localObject
    -0.56
     
    -0.54
    adaptiveStyles
    -0.54
     ProtoMessage
    -0.53
    ⓧ
    -0.53
     &___
    -0.53
    Хьажоргаш
    -0.51
    IntoConstraints
    -0.51
    POSITIVE LOGITS
    argout
    0.33
     '\\;'
    0.30
     кар
    0.30
    +:+
    0.29
    ynb
    0.28
    tinyos
    0.28
    ocarp
    0.28
    这篇
    0.28
    oirs
    0.27
     AW
    0.27
    Act Density 0.183%

    No Known Activations