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

    Neuronpedia

    INDEX
    Explanations

    connections between ideas or concepts within a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lair
    -0.16
     eiusmod
    -0.14
     NOTICE
    -0.14
    ź
    -0.14
    atta
    -0.14
    ure
    -0.14
    agh
    -0.14
    VERTISEMENT
    -0.13
    exampleInputEmail
    -0.13
    essim
    -0.13
    POSITIVE LOGITS
    /how
    0.19
     manner
    0.17
     how
    0.17
    how
    0.16
    ekli
    0.16
    upertino
    0.15
    ndef
    0.15
    sun
    0.14
     Blackburn
    0.14
    _CSR
    0.14
    Act Density 0.134%

    No Known Activations