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

    Neuronpedia

    INDEX
    Explanations

    terms related to mutual agreement or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adge
    -0.16
    خاÙĨÙĩ
    -0.15
    ytic
    -0.15
    names
    -0.14
    unar
    -0.14
    quo
    -0.14
    modo
    -0.14
    exemple
    -0.14
     //////////////////////////////////////////////////////////////////////
    -0.14
    woo
    -0.13
    POSITIVE LOGITS
     upon
    0.29
    ably
    0.24
     Upon
    0.23
    ance
    0.22
    Upon
    0.20
    /dis
    0.20
    upon
    0.20
    able
    0.18
    -up
    0.17
    /ag
    0.17
    Act Density 0.029%

    No Known Activations