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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical lists or sequences

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions, particularly the word "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andem
    -0.62
     Quant
    -0.60
     Epidem
    -0.59
    '>
    -0.59
     Sawyer
    -0.58
    ISA
    -0.58
     Wing
    -0.58
     PUBLIC
    -0.57
     Sage
    -0.57
     wedd
    -0.57
    POSITIVE LOGITS
    oras
    0.71
    ruct
    0.64
    liga
    0.64
    ðŁij
    0.63
    etc
    0.62
    assic
    0.62
    âĶ
    0.61
    bley
    0.61
    akings
    0.60
    ##
    0.60
    Act Density 0.384%

    No Known Activations