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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating a change or new development

    oai_token-act-pair · gpt-3.5-turbo

    verbs and their various forms, particularly focusing on those ending in 's' and 'ing'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ORY
    -0.67
    orsi
    -0.66
    oday
    -0.63
    orest
    -0.63
    IGHTS
    -0.63
     cellar
    -0.62
    è»
    -0.62
     crate
    -0.61
    IFIC
    -0.60
     pots
    -0.58
    POSITIVE LOGITS
    borough
    0.83
    redients
    0.72
    cffffcc
    0.67
    lishes
    0.67
    stellar
    0.67
    lish
    0.66
     Aad
    0.66
    ble
    0.65
     Procedure
    0.63
     Recomm
    0.62
    Act Density 0.119%

    No Known Activations