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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names

    oai_token-act-pair · gpt-3.5-turbo

    the word "am" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "am" (word fragment)

    Explanation Uploaded by User
    New Auto-Interp
    Negative Logits
     stakes
    -0.69
     kinderg
    -0.66
     takeaway
    -0.64
     disadvantage
    -0.64
     puberty
    -0.63
     steroids
    -0.62
     resemb
    -0.62
     ferment
    -0.61
     masks
    -0.61
     cutoff
    -0.60
    POSITIVE LOGITS
    nesty
    1.35
    endment
    1.28
    ilies
    1.19
    sterdam
    1.15
    borgh
    1.08
    pering
    1.04
    essage
    1.02
    urai
    1.02
    bitious
    1.02
    otor
    1.00
    Act Density 0.039%

    No Known Activations