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

    Neuronpedia

    INDEX
    Explanations

    words related to denial or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    are
    -0.62
     Mather
    -0.62
    Fields
    -0.59
    Kind
    -0.59
     Barlow
    -0.58
     Data
    -0.58
    campos
    -0.58
     vectorielle
    -0.57
    atlas
    -0.57
     especie
    -0.56
    POSITIVE LOGITS
    AddTagHelper
    1.18
    "])
    1.02
    theless
    0.99
    )}</
    0.95
    ьаж
    0.93
    featureID
    0.93
    '))
    0.92
    mybatisplus
    0.90
    )),
    0.90
     wasnt
    0.89
    Act Density 0.103%

    No Known Activations