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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    uppercase letters or initialisms, indicating the presence of names, organizations, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.75
    åĤ
    -0.73
     ..."
    -0.70
     ().
    -0.69
     \"
    -0.68
     thereof
    -0.66
     Slayer
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
     laying
    -0.64
     pony
    -0.64
    POSITIVE LOGITS
    resa
    1.13
    ogether
    1.08
    roximately
    0.87
    alyst
    0.87
    anan
    0.84
    ucci
    0.82
    respond
    0.80
     spokeswoman
    0.80
    xiety
    0.79
    withstanding
    0.79
    Act Density 0.358%

    No Known Activations