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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic institutions and political entities

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to organizations or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lur
    -0.71
    Ô
    -0.60
     hereafter
    -0.59
    SPONSORED
    -0.57
     Worlds
    -0.56
     shutdown
    -0.56
    alter
    -0.54
    lift
    -0.53
     Shutdown
    -0.53
     Chronicle
    -0.53
    POSITIVE LOGITS
    ocent
    0.75
    obal
    0.73
    rete
    0.71
    aris
    0.70
    orous
    0.69
    throp
    0.68
    ogn
    0.67
    asonic
    0.67
    inis
    0.66
    athan
    0.66
    Act Density 0.165%

    No Known Activations