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

    Neuronpedia

    INDEX
    Explanations

    words indicating errors or incorrectness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.69
     sober
    -0.64
    +:+
    -0.62
    MLLoader
    -0.52
    XmlAccessType
    -0.51
    UrlResolution
    -0.50
     real
    -0.50
     good
    -0.49
     seamless
    -0.49
     fully
    -0.49
    POSITIVE LOGITS
     inappropriate
    2.28
     incorrect
    2.24
     improper
    2.16
     inadequate
    2.00
     inappropri
    1.97
     Incorrect
    1.96
     insufficient
    1.95
     incorrectly
    1.95
     unsuitable
    1.94
     improperly
    1.92
    Act Density 0.220%

    No Known Activations