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

    Neuronpedia

    INDEX
    Explanations

    references to types of foods and their qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    celik
    -0.16
    erras
    -0.14
    izard
    -0.14
    yen
    -0.14
     Thy
    -0.14
    /browser
    -0.13
     MDMA
    -0.13
    بار
    -0.13
     NAND
    -0.13
    lein
    -0.13
    POSITIVE LOGITS
     heir
    0.31
     slic
    0.27
     determin
    0.27
     slicing
    0.24
     vines
    0.22
     roma
    0.22
     determinant
    0.21
     vine
    0.21
     flesh
    0.21
     Roma
    0.21
    Act Density 0.015%

    No Known Activations