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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a particular manner or approach to doing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe actions or behaviors in relation to comfort and methods of interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MQ
    -0.65
     Thoughts
    -0.65
     Sheet
    -0.61
    ahime
    -0.61
     Ruk
    -0.60
    opa
    -0.60
    onday
    -0.59
     Banking
    -0.59
    raid
    -0.59
    ipping
    -0.58
    POSITIVE LOGITS
     resembles
    1.05
     horr
    1.01
     enables
    0.87
     satisfies
    0.85
     mirrors
    0.83
     enhances
    0.81
     allows
    0.81
     resemble
    0.80
     resembled
    0.80
     inspires
    0.80
    Act Density 0.189%

    No Known Activations