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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific conditions or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gridx
    -0.46
     adicionais
    -0.45
     referenties
    -0.44
    Empty
    -0.44
    ետ
    -0.43
     quedado
    -0.43
    地方
    -0.43
    topper
    -0.43
     vuoto
    -0.42
     parte
    -0.42
    POSITIVE LOGITS
     confines
    1.30
     bounds
    1.02
     framework
    0.99
     boundaries
    0.92
     scope
    0.91
     limits
    0.89
     purview
    0.85
     walls
    0.81
     phạm
    0.80
     Within
    0.77
    Act Density 0.177%

    No Known Activations