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

    Neuronpedia

    INDEX
    Explanations

    references to specific Lego themes and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.67
    kháu
    -0.63
    saraba
    -0.62
     defaultstate
    -0.62
    MigrationBuilder
    -0.61
    Hentet
    -0.56
     heil
    -0.53
    CORBA
    -0.52
     Trout
    -0.50
    argli
    -0.50
    POSITIVE LOGITS
     LEGO
    1.38
     Lego
    1.38
     bricks
    1.34
     Brick
    1.30
     Bricks
    1.25
     lego
    1.22
    Brick
    1.22
     brick
    1.19
    LEGO
    1.17
     minif
    1.17
    Act Density 0.171%

    No Known Activations