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

    Neuronpedia

    INDEX
    Explanations

    references to spatial relations, particularly those involving sides or oppositeness

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.83
     Paglinawan
    -0.79
    InitVars
    -0.78
    ItemBackground
    -0.76
    ✭✭
    -0.75
    lapses
    -0.69
    Demikian
    -0.68
    */;
    -0.67
    êncio
    -0.66
    voyez
    -0.66
    POSITIVE LOGITS
     divide
    0.54
     across
    0.53
    Across
    0.53
     túl
    0.52
     PARSER
    0.50
     Across
    0.49
    across
    0.49
     McFadden
    0.49
     ACROSS
    0.48
     Schles
    0.47
    Act Density 0.015%

    No Known Activations