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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting further exploration, investigation, or discussion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that prompt examination or exploration of a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELD
    -0.87
    Downloadha
    -0.74
    éĹ
    -0.74
    à¨
    -0.72
    CVE
    -0.69
    Unknown
    -0.68
    Course
    -0.68
    BuyableInstoreAndOnline
    -0.65
    ca
    -0.65
    auld
    -0.65
    POSITIVE LOGITS
    amaz
    0.81
    querade
    0.76
     ourselves
    0.75
     rg
    0.71
    acters
    0.67
     reiterate
    0.66
     clarify
    0.64
    00200000
    0.64
    dule
    0.64
     illustrate
    0.63
    Act Density 0.083%

    No Known Activations