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

    Neuronpedia

    INDEX
    Explanations

    terms related to permissions and conditions for usage in legal or copyright contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HostException
    -0.54
    IsContent
    -0.53
    LookAnd
    -0.53
    要不
    -0.52
     Seeder
    -0.51
     invokingState
    -0.51
    criminator
    -0.51
    LabelTagHelper
    -0.51
     VES
    -0.50
     Galvan
    -0.49
    POSITIVE LOGITS
     freely
    0.80
     librement
    0.80
     darf
    0.78
     allowed
    0.70
     Allowed
    0.68
     permitted
    0.67
     permissible
    0.62
    expandindo
    0.61
     libremente
    0.61
     dürfen
    0.61
    Act Density 0.664%

    No Known Activations