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

    Neuronpedia

    INDEX
    Explanations

    references to specific events and their related descriptors or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    937
    -0.17
    ÄįÃŃ
    -0.17
    aginator
    -0.16
    Verifier
    -0.15
    athom
    -0.15
    ÏĨι
    -0.14
    ostat
    -0.14
    å±Ĭ
    -0.14
    acades
    -0.14
    ropolis
    -0.14
    POSITIVE LOGITS
    IDD
    0.15
     Gap
    0.15
    ãģ°ãģĭãĤĬ
    0.15
    íı¬
    0.14
     lah
    0.14
    Gap
    0.14
     antenn
    0.14
     legion
    0.14
    ¡´
    0.14
    ¦¬
    0.13
    Act Density 0.395%

    No Known Activations