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

    Neuronpedia

    INDEX
    Explanations

    capital letters and special characters

    oai_token-act-pair · gpt-3.5-turbo

    sequences of characters or foreign language elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertisement
    -0.65
    glers
    -0.64
    Haunted
    -0.53
    TextColor
    -0.53
    Reviewer
    -0.52
     VIDE
    -0.52
    ModLoader
    -0.52
    âĸĵ
    -0.52
    Magikarp
    -0.51
    inventoryQuantity
    -0.50
    POSITIVE LOGITS
    ande
    0.77
    ensis
    0.66
     lang
    0.56
    uni
    0.56
    arse
    0.55
    anda
    0.55
    eno
    0.52
    zi
    0.52
    ado
    0.50
    bind
    0.50
    Act Density 0.441%

    No Known Activations