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

    Neuronpedia

    INDEX
    Explanations

    acronyms and specific code-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okino
    -0.16
    atial
    -0.15
     heavens
    -0.15
    _serialize
    -0.14
    umat
    -0.14
     Bowman
    -0.14
    owl
    -0.14
    _REFER
    -0.14
    ĸī
    -0.14
    ãĥĭãĤ¢
    -0.14
    POSITIVE LOGITS
    chied
    0.17
    hlen
    0.15
    amarin
    0.15
     Canvas
    0.14
    obra
    0.14
    amet
    0.13
     cru
    0.13
    ships
    0.13
     divis
    0.13
    лав
    0.13
    Act Density 0.514%

    No Known Activations