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

    Neuronpedia

    INDEX
    Explanations

    researchers and authors in scientific contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of research and collaboration among researchers and their teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĸ
    -0.73
    Bound
    -0.70
     Friend
    -0.68
     Vid
    -0.68
     decency
    -0.68
    TRUMP
    -0.66
    VW
    -0.64
     Canaveral
    -0.64
    JP
    -0.63
    SPA
    -0.63
    POSITIVE LOGITS
     hypothes
    1.19
     studied
    1.12
     analyzed
    1.10
     hypothesized
    1.05
     investigated
    1.01
     authors
    1.00
     resear
    0.99
     conducted
    0.99
     analysed
    0.97
     examined
    0.96
    Act Density 0.125%

    No Known Activations