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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating judgment or warning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    947
    -0.17
    aney
    -0.17
    879
    -0.16
    751
    -0.15
    876
    -0.15
    braco
    -0.15
    /REC
    -0.15
    á¿Ĩ
    -0.15
    863
    -0.14
    fleet
    -0.14
    POSITIVE LOGITS
     Plates
    0.23
     Nep
    0.23
     Omni
    0.23
     Ether
    0.22
     Alma
    0.21
     Jared
    0.21
    Ether
    0.20
     plates
    0.20
    plates
    0.19
     Hel
    0.19
    Act Density 0.002%

    No Known Activations