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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating categorization or classification

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest a "sort of" or "kind of" expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essors
    -0.89
    omers
    -0.85
    oons
    -0.84
    years
    -0.83
     Seconds
    -0.83
    ands
    -0.83
    anners
    -0.83
    ients
    -0.82
    inches
    -0.82
    aries
    -0.81
    POSITIVE LOGITS
     consolation
    0.90
     intermediary
    0.86
     existential
    0.84
     miracle
    0.84
     miraculous
    0.84
     ideological
    0.83
     afterlife
    0.82
     magic
    0.82
     mechanism
    0.82
     relationship
    0.80
    Act Density 0.052%

    No Known Activations