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

    Neuronpedia

    INDEX
    Explanations

    words related to gradual progression or change

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gradual changes or progressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brook
    -0.69
    PLIC
    -0.67
    ctions
    -0.67
    ruck
    -0.66
    lands
    -0.65
    youtu
    -0.64
    geon
    -0.63
    quote
    -0.63
    bench
    -0.63
    WT
    -0.63
    POSITIVE LOGITS
     phased
    1.04
     progressively
    0.98
     phases
    0.94
     stages
    0.92
    mental
    0.91
     gradually
    0.90
     gradual
    0.87
     subsequ
    0.84
     "$:/
    0.81
    gradation
    0.80
    Act Density 0.037%

    No Known Activations