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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives that describe the degree of something

    oai_token-act-pair · gpt-3.5-turbo

    references to increasing or enhancing various aspects across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.75
    ipment
    -0.73
    ovie
    -0.69
    liest
    -0.69
    facts
    -0.69
    minus
    -0.68
    comings
    -0.66
    etimes
    -0.65
    atan
    -0.64
    wered
    -0.64
    POSITIVE LOGITS
     efficient
    1.20
     attractive
    1.12
     aggressive
    1.11
     stringent
    1.02
     comfortable
    1.02
     flexible
    1.01
     resilient
    1.00
     ambitious
    1.00
     robust
    1.00
     expensive
    0.99
    Act Density 0.125%

    No Known Activations