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

    Neuronpedia

    INDEX
    Explanations

    adverbs or adverbial phrases indicating a gradual change or progression

    oai_token-act-pair · gpt-3.5-turbo

    terms related to incremental changes or gradual processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IMAGES
    -0.77
     Yorkers
    -0.70
     NL
    -0.69
    gers
    -0.67
    brook
    -0.66
    ctions
    -0.65
     Higgins
    -0.63
    faces
    -0.63
    tein
    -0.63
    sworth
    -0.62
    POSITIVE LOGITS
     phased
    1.01
     gradually
    0.95
    mental
    0.87
     progressively
    0.87
     gradual
    0.86
     "$:/
    0.83
     accumulate
    0.83
     stages
    0.83
     realised
    0.79
    inders
    0.79
    Act Density 0.031%

    No Known Activations