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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases starting with 'at'

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "not at" followed by varying intensity levels in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTWARE
    -0.81
    alpha
    -0.76
    Russ
    -0.71
    gravity
    -0.71
    Lens
    -0.67
    REDACTED
    -0.65
    Pac
    -0.65
    ships
    -0.64
    vous
    -0.63
    eria
    -0.62
    POSITIVE LOGITS
     least
    1.41
    abase
    1.00
    onement
    0.98
    roph
    0.93
    rial
    0.88
     halftime
    0.85
     times
    0.81
    yp
    0.81
    ention
    0.79
    hens
    0.79
    Act Density 0.325%

    No Known Activations