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

    Neuronpedia

    INDEX
    Explanations

    words related to negation and reiteration of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.68
     <<<<<<<<<<<<<<
    -0.65
     виправивши
    -0.63
    cemia
    -0.61
    ajur
    -0.59
    DataAnnotations
    -0.58
    Obrázky
    -0.58
     propOrder
    -0.56
     nuns
    -0.56
    SequentialGroup
    -0.56
    POSITIVE LOGITS
    RegressionTest
    0.59
     kasarigan
    0.59
    jenost
    0.50
     دیکھیے
    0.49
     Hoc
    0.49
    </thead>
    0.48
    InitStruct
    0.45
    lators
    0.45
    oa̍t
    0.44
    StructEnd
    0.43
    Act Density 0.918%

    No Known Activations