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

    Neuronpedia

    INDEX
    Explanations

    phrases that encourage engagement or exploration of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.68
    -0.66
    KURZBESCHREIBUNG
    -0.65
     MessageBoxIcon
    -0.63
     betweenstory
    -0.62
    GEBURTSDATUM
    -0.61
     Infór
    -0.59
     FetchType
    -0.59
     useRouter
    -0.59
     виправивши
    -0.57
    POSITIVE LOGITS
     checkout
    0.69
    Checkout
    0.68
     Checkout
    0.63
    瞧
    0.50
    checkout
    0.50
    ご覧
    0.48
     featured
    0.47
     explore
    0.47
     cool
    0.46
     feature
    0.46
    Act Density 0.091%

    No Known Activations