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

    Neuronpedia

    INDEX
    Explanations

    words related to social structures or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to national identity or collective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    regon
    -0.62
    itton
    -0.60
    []
    -0.60
    /+
    -0.59
    eeee
    -0.58
    LESS
    -0.58
    lah
    -0.55
    Contact
    -0.55
    eor
    -0.55
    SpaceEngineers
    -0.54
    POSITIVE LOGITS
    pires
    1.34
    pired
    1.26
    ociated
    0.98
     portrayed
    0.93
     depicted
    0.91
    pire
    0.87
    uras
    0.87
    ynchron
    0.87
     usual
    0.86
    pects
    0.84
    Act Density 0.085%

    No Known Activations