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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific titles or topics mentioned in the document

    oai_token-act-pair · gpt-3.5-turbo

    titles or names of creative works, particularly songs and literary works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     torpedo
    -0.76
     pickups
    -0.72
     sausage
    -0.70
     loft
    -0.69
     Nelson
    -0.67
    avorite
    -0.65
     salvage
    -0.65
     squats
    -0.65
     estates
    -0.65
     monopoly
    -0.64
    POSITIVE LOGITS
    âĢ
    1.99
    ãĢ
    1.28
    âĢł
    1.27
    âĺ
    1.17
    §
    1.17
    ̶
    1.11
    âĿ
    1.10
    âľ
    1.10
    »
    1.09
    ##
    1.07
    Act Density 0.472%

    No Known Activations