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

    Neuronpedia

    INDEX
    Explanations

    expressions of support and gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omap
    -0.15
    ÌĢ
    -0.15
    AGO
    -0.15
    è¹
    -0.15
     Fol
    -0.15
    Nam
    -0.14
    ิà¸Ļà¸Ĺร
    -0.14
    indle
    -0.14
    елик
    -0.14
    ãģĵãģ¡ãĤī
    -0.14
    POSITIVE LOGITS
     apart
    0.21
     mate
    0.19
     straight
    0.19
     bearing
    0.19
     obviously
    0.18
    everyone
    0.18
     everyone
    0.18
     loads
    0.18
     fingers
    0.17
     credit
    0.17
    Act Density 0.045%

    No Known Activations