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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "te"

    oai_token-act-pair · gpt-3.5-turbo

    the word "te" and its variations used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interrupted
    -0.72
    ipolar
    -0.69
    OST
    -0.69
    lessly
    -0.65
     bottleneck
    -0.64
     obligated
    -0.61
    etheless
    -0.61
    antha
    -0.61
    istically
    -0.60
    usher
    -0.60
    POSITIVE LOGITS
    brate
    1.44
    brates
    1.36
    ller
    1.19
    llers
    1.14
    levision
    1.10
    achers
    1.08
    llo
    1.06
    achable
    1.05
    aching
    1.01
    lla
    0.97
    Act Density 0.027%

    No Known Activations