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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that indicate connections or relationships between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elman
    -0.17
    onders
    -0.15
    onder
    -0.15
    ãģĦãĤĦ
    -0.14
    urum
    -0.14
    (æĹ¥
    -0.14
    oker
    -0.13
    ë»
    -0.13
    cps
    -0.13
    гл
    -0.13
    POSITIVE LOGITS
     alike
    0.23
     etc
    0.22
    etc
    0.18
     respectively
    0.18
    以åıĬ
    0.16
     serta
    0.16
    ãģĿãģĹãģ¦
    0.16
    aroo
    0.14
    /etc
    0.14
     respective
    0.14
    Act Density 0.220%

    No Known Activations