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

    Neuronpedia

    INDEX
    Explanations

    expressions of disappointment or negative emotions

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

    disappoint, await, fail, embarrass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UserModel
    -0.46
    UserModel
    -0.44
     authService
    -0.43
    ,$_
    -0.41
    findpost
    -0.39
     teg
    -0.39
     PDS
    -0.38
     ujednoznacz
    -0.37
     estekak
    -0.37
    WC
    -0.37
    POSITIVE LOGITS
     disappoint
    1.37
    Personensuche
    0.72
     EconPapers
    0.68
     abounds
    0.65
    appoint
    0.60
     abound
    0.56
     haunt
    0.55
     disappointed
    0.55
     delightfully
    0.53
     satisfy
    0.52
    Act Density 0.001%

    No Known Activations