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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "as" used in comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anse
    -0.15
    stagram
    -0.15
    aben
    -0.14
    apolis
    -0.14
    894
    -0.14
    ino
    -0.14
    clock
    -0.14
    天åłĤ
    -0.14
    kontakte
    -0.13
    æł¡
    -0.13
    POSITIVE LOGITS
    eum
    0.17
    umer
    0.15
    keleton
    0.15
    inn
    0.14
    rim
    0.14
     Skeleton
    0.14
    otto
    0.14
     thermometer
    0.14
    _FUNCTIONS
    0.14
    iddy
    0.13
    Act Density 0.028%

    No Known Activations