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

    Neuronpedia

    INDEX
    Explanations

    words related to change and progress

    oai_token-act-pair · gpt-3.5-turbo

    themes related to the future and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indisc
    -0.74
    agram
    -0.68
    ogly
    -0.67
    eger
    -0.67
    imentary
    -0.67
     confidential
    -0.65
    orted
    -0.65
    Sample
    -0.64
    sample
    -0.64
     hairs
    -0.64
    POSITIVE LOGITS
     rebuild
    0.90
     rebuilding
    0.87
     rejuven
    0.87
     reun
    0.87
     Restore
    0.86
    enment
    0.85
     reconciliation
    0.83
     restoring
    0.82
     Zionism
    0.82
    redo
    0.82
    Act Density 0.684%

    No Known Activations