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

    Neuronpedia

    INDEX
    Explanations

    phrases related to common occurrences or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to frequency or prevalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mosp
    -0.96
    zik
    -0.79
    usalem
    -0.78
    endas
    -0.74
    olation
    -0.72
    overe
    -0.71
    thur
    -0.71
     fres
    -0.70
    oÄŁ
    -0.70
    ynthesis
    -0.70
    POSITIVE LOGITS
    wealth
    1.23
    places
    1.06
     denomin
    1.04
    alities
    1.04
    ality
    1.01
     occurrence
    0.96
     occurrences
    0.93
     ancestor
    0.87
    ensical
    0.85
    place
    0.83
    Act Density 0.028%

    No Known Activations