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

    Neuronpedia

    INDEX
    Explanations

    words and prefixes related to the concept of "un" or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ade
    -0.20
     Entr
    -0.15
    ses
    -0.15
    обÑĢаз
    -0.15
    ebek
    -0.15
    whel
    -0.14
    _PAD
    -0.14
    antis
    -0.14
    efficient
    -0.14
    favor
    -0.14
    POSITIVE LOGITS
    wav
    0.22
    wa
    0.22
    erring
    0.22
     wav
    0.21
     w
    0.21
     waiver
    0.21
    ending
    0.20
    uestion
    0.19
     fal
    0.19
     equiv
    0.18
    Act Density 0.030%

    No Known Activations