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

    Neuronpedia

    INDEX
    Explanations

    phrases related to correction and adjustment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bolista
    -0.90
    PerformLayout
    -0.82
     disponibilités
    -0.80
    DockStyle
    -0.80
    Boas
    -0.76
     Мексичка
    -0.76
     Partagez
    -0.76
    ItemBackground
    -0.74
     <<<<<<<<<<<<<<
    -0.73
    Abp
    -0.72
    POSITIVE LOGITS
     Fix
    1.49
    Fix
    1.41
     fix
    1.38
    fix
    1.32
     FIX
    1.30
     fixes
    1.26
     Fixes
    1.21
    Fixes
    1.19
     fixer
    1.18
    fixes
    1.16
    Act Density 0.103%

    No Known Activations