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

    Neuronpedia

    INDEX
    Explanations

    expressions related to the concept of names and naming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ende
    -0.16
    roz
    -0.15
    arend
    -0.15
    ERC
    -0.14
     laid
    -0.14
    pson
    -0.14
    _builtin
    -0.14
    umbn
    -0.14
    illa
    -0.14
    iras
    -0.14
    POSITIVE LOGITS
    稱
    0.15
    ações
    0.15
    ãĤ´ãĥª
    0.15
    DET
    0.14
    \Migration
    0.14
    plib
    0.14
    ously
    0.14
    称
    0.14
    iae
    0.13
     stems
    0.13
    Act Density 0.303%

    No Known Activations