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

    Neuronpedia

    INDEX
    Explanations

    words related to common concepts or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "common" or shared elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udi
    -0.71
    iang
    -0.69
    oby
    -0.68
    agate
    -0.67
    udging
    -0.67
    enda
    -0.67
    hyde
    -0.67
    forestation
    -0.66
    usalem
    -0.66
    otos
    -0.65
    POSITIVE LOGITS
    wealth
    1.20
    alities
    0.95
    ality
    0.90
     ancestor
    0.88
    places
    0.79
     denomin
    0.79
     occurrence
    0.78
    ensical
    0.78
     occurrences
    0.76
     Common
    0.76
    Act Density 0.016%

    No Known Activations