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

    Neuronpedia

    INDEX
    Explanations

    phrases related to thermal activities or controls

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "at" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTWARE
    -0.77
    Pac
    -0.69
    fill
    -0.68
    Lens
    -0.65
    Berry
    -0.61
    birds
    -0.59
    cro
    -0.59
    Iterator
    -0.59
    film
    -0.58
    gravity
    -0.58
    POSITIVE LOGITS
     least
    1.25
    abase
    1.05
    onement
    1.02
    rial
    0.99
    roph
    0.91
    rium
    0.90
    las
    0.85
     halftime
    0.85
    ention
    0.84
     variance
    0.82
    Act Density 0.248%

    No Known Activations