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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "thing"

    oai_token-act-pair · gpt-3.5-turbo

    references to generalized or specific objects, often indicated by the word "thing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     profiles
    -0.75
     Rush
    -0.68
     sensitivity
    -0.65
     deficit
    -0.64
     Listen
    -0.64
     Def
    -0.59
     caps
    -0.58
     families
    -0.57
     screen
    -0.57
     estimates
    -0.57
    POSITIVE LOGITS
    thing
    5.02
    things
    2.12
    THING
    1.49
     Thing
    1.42
     thing
    1.28
    stuff
    1.22
    ths
    1.21
    something
    1.03
    thin
    1.01
    ther
    0.98
    Act Density 0.009%

    No Known Activations