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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political matters

    oai_token-act-pair · gpt-3.5-turbo

    references to social issues and personal actions related to community or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inea
    -0.64
    hetti
    -0.63
    aws
    -0.61
    illes
    -0.59
     Beaut
    -0.58
    netflix
    -0.58
    ezvous
    -0.56
    uses
    -0.55
    /+
    -0.55
    CVE
    -0.55
    POSITIVE LOGITS
    ãĤ«
    0.59
    =~=~
    0.56
    Ó
    0.54
    dial
    0.52
    ãĥ´
    0.50
    ãģĹ
    0.50
    Dial
    0.50
    ĺ
    0.50
    åĪ
    0.50
    ा
    0.50
    Act Density 0.342%

    No Known Activations