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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    social media handles or mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emonium
    -0.78
     circulation
    -0.76
     ordinance
    -0.73
     pneum
    -0.70
     Deliver
    -0.69
     metic
    -0.68
     exhibit
    -0.67
     Dracula
    -0.66
     choir
    -0.66
     corridors
    -0.65
    POSITIVE LOGITS
    realDonaldTrump
    1.17
    #$
    1.13
    @@@@@@@@
    0.99
    groups
    0.95
    TAG
    0.93
    ANI
    0.92
    nat
    0.89
    young
    0.85
    link
    0.83
    gg
    0.82
    Act Density 0.017%

    No Known Activations