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

    Neuronpedia

    INDEX
    Explanations

    entries related to programming functions and commands

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "get" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deduct
    -0.61
     anecd
    -0.59
     Tower
    -0.58
     seals
    -0.57
     deliberations
    -0.57
     slurs
    -0.57
    orough
    -0.55
     exh
    -0.53
    velt
    -0.53
     Diary
    -0.53
    POSITIVE LOGITS
    TING
    1.23
     rid
    1.08
    cloneembedreportprint
    0.98
    tin
    0.92
    away
    0.91
    ãĥ³ãĤ¸
    0.89
    ter
    0.78
    aways
    0.77
    ters
    0.77
    zsche
    0.77
    Act Density 0.046%

    No Known Activations