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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Object" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Object" or derivatives related to computer programming

    oai_token-act-pair · gpt-4-turbo

    references to objects and object-oriented programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oles
    -0.79
    tml
    -0.70
     anthem
    -0.68
    creen
    -0.68
    Ļ½
    -0.66
    icago
    -0.65
     free
    -0.65
    hyde
    -0.64
     tip
    -0.63
     accent
    -0.63
    POSITIVE LOGITS
     Object
    1.11
    ives
    0.95
    Object
    0.85
    uments
    0.83
     Obj
    0.77
    emouth
    0.77
    dump
    0.77
    ive
    0.75
    object
    0.74
    eering
    0.74
    Act Density 0.011%

    No Known Activations