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

    Neuronpedia

    INDEX
    Explanations

    words related to names or identifiers, especially with the suffix "-ard"

    oai_token-act-pair · gpt-3.5-turbo

    words that end with "ard."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     advertised
    -0.60
    pheus
    -0.59
     Orig
    -0.58
     ecstasy
    -0.58
     Underworld
    -0.57
     fold
    -0.57
     processing
    -0.57
     incorporation
    -0.57
     EUR
    -0.56
    */(
    -0.56
    POSITIVE LOGITS
    ard
    4.55
    ards
    3.18
    ARD
    2.72
    ARDS
    2.36
    arding
    2.36
    arded
    2.29
    arde
    2.22
    ardo
    2.15
    ardi
    2.02
    ardy
    1.95
    Act Density 0.012%

    No Known Activations