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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific actions or desires, often with a focus on personal or physical activities

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and pauses in the form of commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ore
    -0.68
    OND
    -0.67
    orer
    -0.65
    oir
    -0.64
    ORE
    -0.63
    оÐ
    -0.63
    Deploy
    -0.63
    Ĥª
    -0.60
    ARCH
    -0.56
    Hy
    -0.56
    POSITIVE LOGITS
     respectively
    0.75
    FontSize
    0.72
     until
    0.65
     but
    0.65
     etc
    0.64
    udeb
    0.64
     disg
    0.63
    into
    0.63
     unless
    0.60
     AMA
    0.60
    Act Density 0.514%

    No Known Activations