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

    Neuronpedia

    INDEX
    Explanations

    high-frequency words that commonly appear in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eba
    -0.18
    ormsg
    -0.17
    173
    -0.15
    .Compiler
    -0.14
    å¹´çļĦ
    -0.14
    Ïĥμα
    -0.14
    ommen
    -0.14
    ¨ë¶Ģ
    -0.14
    .vo
    -0.14
    ìĶ
    -0.14
    POSITIVE LOGITS
    ng
    0.16
    anco
    0.16
    ze
    0.15
     Resistance
    0.15
     ÏĦÏģÏĮ
    0.14
    720
    0.14
    buz
    0.14
     met
    0.14
    ,'#
    0.14
    icode
    0.14
    Act Density 0.001%

    No Known Activations