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

    Neuronpedia

    INDEX
    Explanations

    references to programming languages and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prov
    -0.17
    ancel
    -0.16
     il
    -0.15
    enco
    -0.15
     rejo
    -0.15
    encoding
    -0.15
    511
    -0.15
    uther
    -0.15
    911
    -0.14
     cray
    -0.14
    POSITIVE LOGITS
    azioni
    0.28
    amenti
    0.25
    zioni
    0.23
    izioni
    0.22
    enze
    0.22
    ografie
    0.22
    getti
    0.21
    contri
    0.20
    ioni
    0.20
    conti
    0.20
    Act Density 0.018%

    No Known Activations