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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles and usernames

    oai_token-act-pair · gpt-3.5-turbo

    usernames or handles associated with social media accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Levant
    -0.72
    anwhile
    -0.71
     electronically
    -0.63
     Uriel
    -0.60
     Bashar
    -0.60
     Avalon
    -0.58
     lobbying
    -0.56
     anonymously
    -0.55
     PACs
    -0.55
     Frankenstein
    -0.54
    POSITIVE LOGITS
    dL
    1.09
    ZI
    1.06
    dq
    1.05
    ZX
    1.01
    9
    1.00
    0
    1.00
    zx
    0.98
    qq
    0.97
    8
    0.97
    Q
    0.96
    Act Density 0.059%

    No Known Activations