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

    Neuronpedia

    INDEX
    Explanations

    references to authority or oversight in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guise
    -0.86
     auspices
    -0.85
    -0.59
     pretext
    -0.56
     estekak
    -0.54
     ausp
    -0.52
    -0.50
    DataAnnotations
    -0.47
     aegis
    -0.47
    ंदीखरीदारी
    -0.45
    POSITIVE LOGITS
    VersionUID
    0.46
    StoryboardSegue
    0.43
     Winaray
    0.39
     repelled
    0.39
    hadap
    0.38
    ice
    0.38
     gitu
    0.38
    EndContext
    0.37
     TResult
    0.36
    scal
    0.36
    Act Density 0.003%

    No Known Activations