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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate exceptions or conditions in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovy
    -0.16
    ÑģÑĤÑİ
    -0.16
    swers
    -0.16
    gnu
    -0.15
    jer
    -0.15
    опол
    -0.14
    iang
    -0.14
    alaxy
    -0.14
     Desert
    -0.14
    odable
    -0.14
    POSITIVE LOGITS
     otherwise
    0.33
     noted
    0.33
     stated
    0.32
     indicated
    0.32
     explicitly
    0.28
     specifically
    0.27
    otherwise
    0.26
     expressly
    0.25
     specified
    0.24
     indicate
    0.24
    Act Density 0.032%

    No Known Activations