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

    Neuronpedia

    INDEX
    Explanations

    the word "aid"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "aid."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caliber
    -0.67
     Pes
    -0.65
    =-=-=-=-=-=-=-=-
    -0.64
     Superior
    -0.63
     Olympia
    -0.63
     Grind
    -0.62
    VAL
    -0.60
     Armed
    -0.60
     goddamn
    -0.59
     Stras
    -0.59
    POSITIVE LOGITS
    aid
    1.40
    ayer
    1.10
    doms
    0.85
    mand
    0.85
    arine
    0.82
    irst
    0.80
    ayers
    0.80
    idas
    0.78
    irection
    0.77
    aily
    0.76
    Act Density 0.009%

    No Known Activations