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

    Neuronpedia

    INDEX
    Explanations

    phrases related to misconceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elman
    -0.18
    alking
    -0.16
     Hav
    -0.16
    ÏĦη
    -0.15
     Nem
    -0.15
     BitmapFactory
    -0.15
    bersome
    -0.15
    acons
    -0.14
    uncan
    -0.14
     Emer
    -0.14
    POSITIVE LOGITS
    ceptions
    0.37
    ceived
    0.28
     con
    0.23
    ception
    0.22
    CEPTION
    0.21
    preh
    0.20
    cie
    0.20
    concept
    0.18
    cep
    0.18
    ceive
    0.18
    Act Density 0.007%

    No Known Activations