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

    Neuronpedia

    INDEX
    Explanations

    items related to RPG games and gaming elements

    oai_token-act-pair · gpt-3.5-turbo

    gaming-related terms and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.89
     enthusi
    -0.72
     reluct
    -0.68
     ambassadors
    -0.67
     advoc
    -0.67
    senal
    -0.64
    undown
    -0.61
     ambitious
    -0.58
     policing
    -0.58
     catering
    -0.57
    POSITIVE LOGITS
    /(
    1.05
     âĨĴ
    1.04
     ->
    0.98
     :=
    0.95
     !=
    0.94
     =
    0.93
     (-
    0.93
     [+
    0.91
     ==
    0.89
     (=
    0.89
    Act Density 0.678%

    No Known Activations