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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the lifting of restrictions or bans

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of lifting, elevating, or removing restrictions and barriers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    errilla
    -0.77
    lished
    -0.70
    present
    -0.66
    Future
    -0.65
    ãĥ£
    -0.64
    printf
    -0.63
    perture
    -0.62
    TAG
    -0.62
    915
    -0.62
    Cola
    -0.62
    POSITIVE LOGITS
     weights
    1.07
     lift
    1.02
     lifting
    0.99
     lifted
    0.96
     lifts
    0.88
    lift
    0.80
    hens
    0.79
     tremend
    0.78
    hetically
    0.77
    weight
    0.77
    Act Density 0.024%

    No Known Activations