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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic research and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Franti
    -0.16
    ertz
    -0.16
    cie
    -0.15
    عÙģ
    -0.14
    èĬ³
    -0.14
    Ñĸ
    -0.13
    tsky
    -0.13
    tah
    -0.13
     Micha
    -0.13
    uat
    -0.13
    POSITIVE LOGITS
    wi
    0.15
    omed
    0.15
    ãĥ¡ãĥ³ãĥĪ
    0.14
    ิà¸ĩ
    0.14
    webs
    0.14
    åıĬåħ¶
    0.14
    wit
    0.14
    olik
    0.13
    omet
    0.13
    .volley
    0.13
    Act Density 0.321%

    No Known Activations