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

    Neuronpedia

    INDEX
    Explanations

    repeated references to various studies and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odcast
    -0.15
     hands
    -0.15
    odus
    -0.14
    Ư
    -0.14
    pic
    -0.14
    ouch
    -0.14
    omit
    -0.14
    heit
    -0.14
    panse
    -0.14
    aign
    -0.14
    POSITIVE LOGITS
     Congress
    0.16
    egas
    0.15
    etrofit
    0.15
    Congress
    0.14
    oeff
    0.14
    æľ
    0.14
    GD
    0.14
    riminator
    0.13
    relationships
    0.13
    orning
    0.13
    Act Density 0.054%

    No Known Activations