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

    Neuronpedia

    INDEX
    Explanations

    phrases related to achievements and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĬات
    -0.16
    kees
    -0.15
    airo
    -0.15
    atcher
    -0.15
    aley
    -0.15
    iga
    -0.14
     Retrofit
    -0.14
    umbledore
    -0.14
    sgi
    -0.14
    tes
    -0.14
    POSITIVE LOGITS
    ollen
    0.19
    owski
    0.18
     invariant
    0.15
    'gc
    0.15
    prim
    0.14
     awarded
    0.14
     Laz
    0.14
    RectTransform
    0.14
    ague
    0.13
     awards
    0.13
    Act Density 0.330%

    No Known Activations