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

    Neuronpedia

    INDEX
    Explanations

    expressive phrases and interjections, often conveying emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressive, stylized short phrases—often in quotes—especially interjections, dialectal or foreign-language wording, and internet-slang forms.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.67
    -0.58
    RTLI
    -0.58
    RegistryLite
    -0.54
    glected
    -0.53
     protoimpl
    -0.51
     picioare
    -0.50
     queſta
    -0.48
     brugt
    -0.48
     BytesLike
    -0.48
    POSITIVE LOGITS
     betweenstory
    0.44
     God
    0.41
     Yes
    0.34
     PERIOD
    0.33
    God
    0.33
     todo
    0.33
    argout
    0.32
    WaitGroup
    0.32
     turno
    0.32
    Yes
    0.31
    Act Density 0.342%

    No Known Activations