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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disciplinary actions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.78
    tvguidetime
    -0.73
    клопе
    -0.73
    WebVitals
    -0.68
    AutoField
    -0.67
    InSection
    -0.65
     CreateTagHelper
    -0.63
    NameInMap
    -0.62
     sneaky
    -0.62
     IBOutlet
    -0.62
    POSITIVE LOGITS
    ItemBackground
    0.53
    Statement
    0.46
     announced
    0.45
    ременно
    0.44
     fullt
    0.42
    ...
    0.41
    rmtree
    0.41
    Toolbar
    0.41
    isEnd
    0.41
    ercises
    0.40
    Act Density 0.282%

    No Known Activations