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

    Neuronpedia

    INDEX
    Explanations

    references to academic titles and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oby
    -0.18
    лой
    -0.18
    itters
    -0.15
     ActionTypes
    -0.15
    rais
    -0.14
    staw
    -0.14
    ses
    -0.14
    ning
    -0.14
    steder
    -0.14
    cape
    -0.13
    POSITIVE LOGITS
    -dom
    0.16
    /sub
    0.16
    /Sub
    0.15
    upp
    0.14
    umber
    0.14
    wt
    0.14
    aint
    0.14
    /group
    0.14
    ages
    0.14
    mates
    0.14
    Act Density 0.010%

    No Known Activations