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

    Neuronpedia

    INDEX
    Explanations

    terms related to competence and competence-related judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ัà¸Ļà¸Ļ
    -0.14
    t
    -0.14
     Dut
    -0.14
     momentum
    -0.14
    å²
    -0.14
     Rek
    -0.13
     Dias
    -0.13
    eel
    -0.13
     Cruc
    -0.13
     submits
    -0.13
    POSITIVE LOGITS
    mons
    0.17
    odate
    0.15
    615
    0.15
    надлеж
    0.14
    achie
    0.14
    clide
    0.14
    phis
    0.14
    _SIGNATURE
    0.14
    -properties
    0.14
     suce
    0.14
    Act Density 0.005%

    No Known Activations