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

    Neuronpedia

    INDEX
    Explanations

    comparisons expressed with the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antis
    -0.18
    GED
    -0.16
    ãģ£ãģį
    -0.14
    mony
    -0.14
    timeofday
    -0.14
    opolitan
    -0.14
    istrovstvÃŃ
    -0.14
    osten
    -0.14
    _NV
    -0.14
     phóng
    -0.14
    POSITIVE LOGITS
    üp
    0.17
    uto
    0.15
    /to
    0.14
     manner
    0.14
     con
    0.14
     bil
    0.14
    sg
    0.14
    oci
    0.13
    uten
    0.13
     Nav
    0.13
    Act Density 0.038%

    No Known Activations