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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate exception or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gne
    -0.17
    odyn
    -0.17
    hei
    -0.16
    odb
    -0.16
     con
    -0.15
    BoundingClientRect
    -0.15
    isoft
    -0.15
    hani
    -0.14
    labs
    -0.14
    ADC
    -0.14
    POSITIVE LOGITS
    gary
    0.17
     anymore
    0.17
     nor
    0.17
    erek
    0.17
     unt
    0.15
     gear
    0.14
    nor
    0.14
    िà¤ļ
    0.14
    locker
    0.14
    nis
    0.14
    Act Density 0.080%

    No Known Activations