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

    Neuronpedia

    INDEX
    Explanations

    references to specific people's roles or positions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Boca
    -0.16
     Taco
    -0.15
    buquerque
    -0.15
    Ohio
    -0.14
    riere
    -0.14
     taco
    -0.14
    iks
    -0.14
    ObjectContext
    -0.14
    apas
    -0.14
     Foo
    -0.13
    POSITIVE LOGITS
     Anne
    0.39
    Anne
    0.33
     Gilbert
    0.30
     anne
    0.28
     Montgomery
    0.26
    anne
    0.26
     Mar
    0.20
     Av
    0.20
     orphan
    0.20
     Green
    0.20
    Act Density 0.011%

    No Known Activations