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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or processes that involve intense activity or change

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "create" or related verb forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bring
    -0.58
     neigh
    -0.58
     prod
    -0.56
     unlock
    -0.55
    rock
    -0.55
    gear
    -0.55
    bring
    -0.54
     visibility
    -0.53
     raise
    -0.52
     Ung
    -0.51
    POSITIVE LOGITS
    ated
    4.14
    ating
    2.74
    ATED
    2.46
    ates
    2.30
    ation
    2.12
    ate
    2.09
    ATING
    1.89
    ations
    1.87
    ator
    1.84
    ators
    1.79
    Act Density 0.017%

    No Known Activations