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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to large-scale concepts or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Minerva
    -0.66
     Congo
    -0.65
     Keeper
    -0.64
     Cortana
    -0.64
     Cambodia
    -0.63
     Catalyst
    -0.62
     Yel
    -0.62
     Shutterstock
    -0.62
     Fidel
    -0.62
     Queens
    -0.62
    POSITIVE LOGITS
    scale
    1.45
    bodied
    1.39
    sized
    1.19
    enough
    1.17
    sounding
    1.12
    capacity
    1.10
    eyed
    1.08
    dollar
    1.05
    sided
    1.05
    budget
    1.01
    Act Density 0.062%

    No Known Activations