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

    Neuronpedia

    INDEX
    Explanations

    descriptions of individuals and their actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe individuals and their situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nutshell
    -0.69
     concluding
    -0.67
     Readers
    -0.62
     roadmap
    -0.59
    anners
    -0.59
     billboards
    -0.57
     Dice
    -0.56
     Catch
    -0.56
     Recovery
    -0.55
    ainers
    -0.55
    POSITIVE LOGITS
    upon
    0.91
    Äĩ
    0.83
     whom
    0.78
     specializes
    0.78
     nearby
    0.77
    unknown
    0.76
    nown
    0.76
     presumably
    0.74
     likewise
    0.74
    likely
    0.72
    Act Density 0.414%

    No Known Activations