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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and symbols within code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kowski
    -0.17
    oulos
    -0.16
    childs
    -0.16
    zin
    -0.15
    odes
    -0.15
    _ATTRIB
    -0.15
    æĺĩ
    -0.14
     دÙĪر
    -0.14
    elial
    -0.14
    ále
    -0.14
    POSITIVE LOGITS
    ibri
    0.15
    oming
    0.15
    omen
    0.15
     vapor
    0.15
    ampton
    0.14
     ÙģرÙĪدگاÙĩ
    0.14
    umbn
    0.14
     Brid
    0.14
     Magn
    0.14
    omnia
    0.14
    Act Density 0.001%

    No Known Activations