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

    Neuronpedia

    INDEX
    Explanations

    numerical and formatting patterns in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.52
    TemporalType
    -0.50
     zelve
    -0.47
    GenerationType
    -0.44
    ftagPool
    -0.44
    IMPORTED
    -0.41
    hitheatre
    -0.41
    ioutil
    -0.41
    QMetaType
    -0.41
    CORBA
    -0.40
    POSITIVE LOGITS
    ſelves
    0.51
     houſe
    0.48
     ब्रेकडाउन
    0.43
     ujednoznacz
    0.42
     ddelweddau
    0.41
     Monfieur
    0.41
     Eps
    0.40
     fhort
    0.40
     ſmall
    0.40
     infallible
    0.40
    Act Density 0.360%

    No Known Activations