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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performing tasks or activities one step at a time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal processes and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.70
    urities
    -0.67
    ForgeModLoader
    -0.65
     Vi
    -0.63
     Wa
    -0.60
    ription
    -0.60
    اÙĦ
    -0.59
     Amon
    -0.56
    ilities
    -0.55
     unseen
    -0.55
    POSITIVE LOGITS
     apiece
    1.25
     per
    0.94
    poons
    0.87
    secut
    0.86
    ches
    0.82
     totaling
    0.82
     shy
    0.76
    illion
    0.75
     consecut
    0.75
     worth
    0.73
    Act Density 0.671%

    No Known Activations