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

    Neuronpedia

    INDEX
    Explanations

    financial allocations and statements related to funding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     osm
    -0.16
     Podesta
    -0.16
     Zucker
    -0.14
    anken
    -0.14
    551
    -0.14
     Jord
    -0.14
     Columbia
    -0.14
    Ñī
    -0.14
     ocean
    -0.14
    ulis
    -0.14
    POSITIVE LOGITS
     Manip
    0.39
    Manip
    0.26
     manip
    0.24
     Ass
    0.24
     Miz
    0.23
     Dim
    0.22
     Northeast
    0.22
     manipulation
    0.21
    -Ass
    0.21
     Nag
    0.20
    Act Density 0.031%

    No Known Activations