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

    Neuronpedia

    INDEX
    Explanations

    words related to different choices or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    various options and alternatives available in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OV
    -0.70
    onel
    -0.64
    Writ
    -0.63
    Untitled
    -0.62
    oned
    -0.61
    adelphia
    -0.60
    Die
    -0.60
    enged
    -0.59
    athon
    -0.58
    ograph
    -0.57
    POSITIVE LOGITS
    cale
    1.17
    etting
    1.14
    paces
    1.14
    pring
    1.13
    pace
    1.13
     abound
    1.10
    ensical
    1.04
    ourcing
    1.01
    ystem
    1.00
    olutions
    0.94
    Act Density 0.291%

    No Known Activations