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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific actions and discussions in a community or society

    oai_token-act-pair · gpt-3.5-turbo

    various forms of numerical or statistical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     emperor
    -0.83
     derog
    -0.81
     traitor
    -0.81
     treason
    -0.79
     deliber
    -0.78
     assassin
    -0.78
     aven
    -0.78
     reflex
    -0.77
     consum
    -0.77
     occult
    -0.76
    POSITIVE LOGITS
    But
    1.46
    Residents
    1.46
    Instead
    1.42
    Copyright
    1.39
    Some
    1.39
    They
    1.37
    Currently
    1.36
    Because
    1.36
    Advertisement
    1.36
    Owner
    1.36
    Act Density 0.486%

    No Known Activations