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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a large quantity or variety of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    念
    -0.15
    itian
    -0.14
    ược
    -0.14
    .air
    -0.14
    ilet
    -0.14
    еÑĢин
    -0.13
    ihn
    -0.13
     Termin
    -0.13
    gamber
    -0.13
    iya
    -0.13
    POSITIVE LOGITS
     ways
    0.23
     reasons
    0.19
    ways
    0.17
     Reasons
    0.16
     Ways
    0.16
     zad
    0.15
    .INSTANCE
    0.15
    iel
    0.15
     Dün
    0.15
     reason
    0.15
    Act Density 0.080%

    No Known Activations