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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ξε
    -0.57
    φε
    -0.55
     Ken
    -0.53
    爱的
    -0.52
    ==
    -0.51
    ('<
    -0.51
    зил
    -0.50
     Hayes
    -0.50
    <<
    -0.50
     Erskine
    -0.50
    POSITIVE LOGITS
    theless
    1.21
     defaultstate
    1.11
     ProtoMessage
    0.98
    AddTagHelper
    0.96
    #+#
    0.95
     unknownFields
    0.93
    verständlich
    0.93
    owohl
    0.89
    jalá
    0.88
    +#+#
    0.87
    Act Density 0.038%

    No Known Activations