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

    Neuronpedia

    INDEX
    Explanations

    references to specific models or components in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.54
     […]
    -0.53
     
    -0.50
      
    -0.50
    riturismo
    -0.49
    greSQL
    -0.49
    VELAND
    -0.49
     just
    -0.48
    …
    -0.47
     oublier
    -0.47
    POSITIVE LOGITS
     Reſ
    1.29
    ſelf
    1.24
     Diſ
    1.22
    ſelves
    1.21
     Majefty
    1.19
     Inſ
    1.16
     Houſe
    1.16
     Perſ
    1.14
     houſe
    1.13
     ſche
    1.12
    Act Density 0.834%

    No Known Activations