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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments and emotions expressed in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.61
    хьтан
    -0.58
    rrggbb
    -0.58
    mobileqq
    -0.58
    KommentareTeilen
    -0.56
    etcode
    -0.56
    urlpatterns
    -0.54
    NOPE
    -0.54
     viewDidLoad
    -0.54
    Scripture
    -0.53
    POSITIVE LOGITS
     evidences
    0.82
     few
    0.80
     equipments
    0.67
    Few
    0.66
     convenable
    0.65
     advices
    0.65
    few
    0.64
     different
    0.63
    fører
    0.62
     researches
    0.59
    Act Density 0.841%

    No Known Activations