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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" and its contextual significance in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lolita
    -0.66
    stdc
    -0.63
     certiorari
    -0.62
     pleaf
    -0.62
     Holi
    -0.60
    บัติ
    -0.59
    bonucleic
    -0.58
    tvguidetime
    -0.58
     Jot
    -0.58
     baptis
    -0.58
    POSITIVE LOGITS
     that
    0.66
     وأن
    0.59
    ntä
    0.55
     consequently
    0.55
     szükség
    0.54
    #+#
    0.54
     насељу
    0.53
     therefore
    0.52
     unknownFields
    0.52
     évent
    0.52
    Act Density 0.218%

    No Known Activations