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

    Neuronpedia

    INDEX
    Explanations

    references to caution and guidance in communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.85
     @"/
    -0.72
    AddTagHelper
    -0.71
    Хьажоргаш
    -0.70
     cherchés
    -0.68
     OMIT
    -0.67
    MigrationBuilder
    -0.63
    HttpPut
    -0.61
    setVerticalGroup
    -0.60
    NameInMap
    -0.58
    POSITIVE LOGITS
     yourself
    0.80
    yourself
    0.62
    Yourself
    0.61
    chedelic
    0.61
     yourselves
    0.60
    acabana
    0.60
     preferably
    0.59
     Yourself
    0.57
     Preferably
    0.57
     Alternatively
    0.57
    Act Density 0.294%

    No Known Activations