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

    Neuronpedia

    INDEX
    Explanations

    verbs relating to continuous or repeated actions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to persistence and continuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bin
    -0.69
    NER
    -0.69
    iera
    -0.68
    blogspot
    -0.68
    ternity
    -0.67
    ibaba
    -0.66
    liest
    -0.66
    bia
    -0.66
    iquette
    -0.64
    fell
    -0.63
    POSITIVE LOGITS
     pursu
    0.69
    cium
    0.68
     productive
    0.67
     Seah
    0.67
    rued
    0.64
     Squid
    0.64
    repeat
    0.62
    ussions
    0.61
    ãĥ¥
    0.61
     constant
    0.61
    Act Density 0.061%

    No Known Activations