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

    Neuronpedia

    INDEX
    Explanations

    references to studies and their findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sometimes
    -0.70
     Sometimes
    -0.67
    oznam
    -0.63
    Sometimes
    -0.63
    sometimes
    -0.61
    amię
    -0.57
    Véxase
    -0.55
     jadx
    -0.55
     suele
    -0.54
     often
    -0.54
    POSITIVE LOGITS
     novel
    0.81
     novelty
    0.71
    novel
    0.69
     methodology
    0.66
     noved
    0.65
     contribution
    0.64
     propose
    0.64
     aimed
    0.63
     endeavoured
    0.63
     ambiti
    0.59
    Act Density 1.262%

    No Known Activations