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

    Neuronpedia

    INDEX
    Explanations

    names of people and concepts related to politics, economics, or academia

    oai_token-act-pair · gpt-3.5-turbo

    names of well-known figures and entities, particularly in the context of discussions or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     skelet
    -0.74
     UNCLASSIFIED
    -0.72
     disadvant
    -0.59
    etheless
    -0.58
     exting
    -0.57
     pse
    -0.57
    âķIJ
    -0.56
     Azerb
    -0.54
    âĹ¼
    -0.54
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.54
    POSITIVE LOGITS
     [âĢ¦]
    0.70
     âĢİ
    0.65
    âĢİ
    0.61
     âĢº
    0.58
     Donald
    0.54
    ↵Âł
    0.53
     ....
    0.51
     Posted
    0.51
     ...
    0.48
    20439
    0.48
    Act Density 6.016%

    No Known Activations