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

    Neuronpedia

    INDEX
    Explanations

    words related to impressions or impactful experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QUENCE
    -0.17
    ched
    -0.16
    ering
    -0.15
    kup
    -0.15
    iders
    -0.15
    ijing
    -0.15
    INGS
    -0.15
    हर
    -0.15
    ered
    -0.14
    quette
    -0.14
    POSITIVE LOGITS
     Imp
    0.25
    .Imp
    0.21
     imp
    0.20
    Imp
    0.20
    _imp
    0.17
     имп
    0.17
    .imp
    0.17
    rompt
    0.17
    ala
    0.17
     Im
    0.17
    Act Density 0.014%

    No Known Activations