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

    Neuronpedia

    INDEX
    Explanations

    questions that imply uncertainty or request clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Greater
    -0.16
    -One
    -0.14
     Independence
    -0.14
    KT
    -0.14
     Hispanic
    -0.14
    imax
    -0.14
     Vernon
    -0.14
     IHttp
    -0.13
    REP
    -0.13
    ivery
    -0.13
    POSITIVE LOGITS
     van
    0.19
     Mac
    0.18
     Sands
    0.17
     de
    0.17
     Ferrari
    0.17
     Sch
    0.17
     Perl
    0.17
     Jones
    0.17
     Ba
    0.17
     K
    0.17
    Act Density 2.786%

    No Known Activations