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

    Neuronpedia

    INDEX
    Explanations

    terms related to selective processing and filtering of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.90
     Efq
    -0.88
     myſelf
    -0.85
     themſelves
    -0.80
     faſt
    -0.77
     himſelf
    -0.77
    ſelf
    -0.76
     ſhe
    -0.75
     ſeveral
    -0.74
     defStyle
    -0.73
    POSITIVE LOGITS
     selective
    0.83
     selectively
    0.80
     Selective
    0.75
     sele
    0.75
     select
    0.70
    selective
    0.62
    Selective
    0.61
     selection
    0.60
    select
    0.60
    sele
    0.57
    Act Density 0.975%

    No Known Activations