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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote examples or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyas
    -0.17
    egan
    -0.15
    737
    -0.15
    composite
    -0.14
    [#
    -0.14
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    -0.14
    SystemService
    -0.14
    ¢
    -0.14
    zdy
    -0.13
    zd
    -0.13
    POSITIVE LOGITS
     solid
    0.15
    ellar
    0.15
    !/
    0.14
     solidity
    0.14
     hur
    0.14
    arie
    0.14
    981
    0.14
     trop
    0.14
    acus
    0.14
     vir
    0.13
    Act Density 0.060%

    No Known Activations