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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or contrast, particularly related to statements or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alytics
    -0.16
     Verd
    -0.14
    owo
    -0.14
    -toggler
    -0.14
    cept
    -0.14
    Controls
    -0.14
    orce
    -0.14
    kur
    -0.14
    AMP
    -0.13
     kvinne
    -0.13
    POSITIVE LOGITS
     presence
    0.16
    presence
    0.15
    inium
    0.15
    ãĤµãĤ¤
    0.14
    änger
    0.14
    imming
    0.14
     Earn
    0.14
    _IMPL
    0.14
    visor
    0.14
    ismo
    0.14
    Act Density 0.032%

    No Known Activations