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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fundamental concepts, basic principles, and essential knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _based
    -0.18
    sdale
    -0.17
     basically
    -0.16
    pecific
    -0.16
    SWG
    -0.15
    Base
    -0.15
    åŁºåľ°
    -0.15
    ;base
    -0.15
    specific
    -0.14
     Specialists
    -0.14
    POSITIVE LOGITS
     ten
    0.28
     premise
    0.28
     tenants
    0.28
     principles
    0.28
     tenant
    0.26
     principle
    0.24
    -level
    0.24
     principals
    0.24
     necessities
    0.24
     concepts
    0.23
    Act Density 0.057%

    No Known Activations