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

    Neuronpedia

    INDEX
    Explanations

    negative phrases and qualifiers indicating limitations or denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !*\
    -0.59
     Rath
    -0.47
    inafter
    -0.43
     Ph
    -0.43
    .
    -0.42
    php
    -0.42
    満
    -0.41
    E
    -0.40
     recevez
    -0.40
    知
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.83
    GEBURTSDATUM
    0.78
    CompilerServices
    0.75
    utilisons
    0.75
     gyhoeddwyd
    0.72
     صوتيه
    0.72
    تقاوى
    0.70
    Personendaten
    0.69
     autorytatywna
    0.68
     CreateTagHelper
    0.68
    Act Density 0.343%

    No Known Activations