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

    Neuronpedia

    INDEX
    Explanations

    anonymous mentions or credit attributions

    oai_token-act-pair · gpt-3.5-turbo

    references to authorship or attributions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    negie
    -0.78
    ablish
    -0.73
    utical
    -0.73
    psc
    -0.73
    wcsstore
    -0.72
    Interstitial
    -0.71
    ãĥīãĥ©
    -0.71
    inatory
    -0.71
    =~=~
    -0.70
    EStream
    -0.70
    POSITIVE LOGITS
     commenter
    1.56
     reader
    1.32
     commenters
    1.21
     blogger
    1.18
     Redd
    1.08
     commentator
    1.06
     someone
    1.06
     columnist
    1.05
     reviewer
    1.04
     contributor
    1.03
    Act Density 0.307%

    No Known Activations