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

    Neuronpedia

    INDEX
    Explanations

    phrases enclosed by quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks, indicating direct speech or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alger
    -0.74
     derby
    -0.69
     posting
    -0.69
     publishing
    -0.66
     fury
    -0.65
     affiliate
    -0.65
     Gaal
    -0.65
     Crane
    -0.65
     seasoned
    -0.64
     shaking
    -0.64
    POSITIVE LOGITS
    almost
    1.10
    every
    1.09
    extremely
    1.03
    little
    1.02
    highly
    1.01
    moderate
    1.00
    self
    1.00
    super
    1.00
    never
    0.99
    their
    0.99
    Act Density 0.134%

    No Known Activations