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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical definitions and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ridley
    -0.17
    /tos
    -0.16
    alten
    -0.15
     Oc
    -0.15
     OCC
    -0.15
    anken
    -0.15
     LDL
    -0.14
     Themes
    -0.14
    .findViewById
    -0.13
    ören
    -0.13
    POSITIVE LOGITS
     Äiju
    0.16
    HEMA
    0.15
    rax
    0.15
    ÑĨип
    0.14
    ãĥ³ãĥī
    0.14
     Correct
    0.14
    uti
    0.14
    ุà¸ģ
    0.14
    aight
    0.13
    923
    0.13
    Act Density 0.050%

    No Known Activations