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

    Neuronpedia

    INDEX
    Explanations

    quotes or statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    statements attributed to various sources or officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =~=~
    -0.84
    ï¸
    -0.73
    ptives
    -0.71
    WithNo
    -0.70
     Himself
    -0.70
    thia
    -0.70
    llular
    -0.70
    Issue
    -0.68
     ILCS
    -0.68
    Interstitial
    -0.66
    POSITIVE LOGITS
     goodbye
    1.03
    doms
    0.89
     anecd
    0.71
     majorities
    0.68
     they
    0.67
    inery
    0.65
     fortunes
    0.62
     hello
    0.60
     Michaels
    0.60
    rons
    0.59
    Act Density 0.198%

    No Known Activations