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

    Neuronpedia

    INDEX
    Explanations

    phrases related to control and authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to compliance and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unta
    -0.69
     Archdemon
    -0.68
    razil
    -0.67
    ctors
    -0.62
     nude
    -0.60
    tymology
    -0.59
     Phant
    -0.58
    anto
    -0.57
    ierre
    -0.57
     Aware
    -0.56
    POSITIVE LOGITS
     happening
    0.91
     fruition
    0.88
     occurring
    0.82
     happen
    0.72
     eroded
    0.67
     flowing
    0.65
     undone
    0.65
     occur
    0.62
     unanswered
    0.62
     reverber
    0.62
    Act Density 1.041%

    No Known Activations