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

    Neuronpedia

    INDEX
    Explanations

    acronyms or abbreviations followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Int" along with related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     landfill
    -0.77
     abolition
    -0.68
     derby
    -0.68
     councillor
    -0.67
     legend
    -0.66
     yours
    -0.66
     worker
    -0.65
     lettuce
    -0.64
     fallen
    -0.64
     pencil
    -0.64
    POSITIVE LOGITS
    Int
    3.71
     Int
    1.81
    INT
    1.64
    Float
    1.61
    int
    1.58
    Str
    1.40
     INT
    1.35
     Intent
    1.34
    intelligence
    1.30
    Boo
    1.27
    Act Density 0.009%

    No Known Activations