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

    Neuronpedia

    INDEX
    Explanations

    words related to approval and endorsement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynos
    -0.17
    ideon
    -0.15
    anny
    -0.15
    ieren
    -0.15
    ii
    -0.14
    ugu
    -0.14
    yer
    -0.14
    sin
    -0.14
    eton
    -0.14
    umann
    -0.13
    POSITIVE LOGITS
    ebek
    0.21
    eck
    0.18
    º
    0.16
    uzz
    0.15
    apesh
    0.15
     escorte
    0.14
    .transport
    0.14
    åĽ
    0.14
    èĤĸ
    0.14
    obraz
    0.14
    Act Density 0.006%

    No Known Activations