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

    Neuronpedia

    INDEX
    Explanations

    phrases related to knowledge

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge and its various aspects or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ishable
    -0.65
    etheus
    -0.62
    headers
    -0.62
    avored
    -0.60
    itter
    -0.60
    issions
    -0.59
    interstitial
    -0.59
    odder
    -0.58
    cers
    -0.57
    gm
    -0.57
    POSITIVE LOGITS
    ledge
    1.16
    lege
    1.13
    fulness
    0.95
    ledged
    0.83
     glean
    0.81
    reading
    0.81
    liness
    0.80
    fully
    0.80
     knowledge
    0.79
    lessness
    0.77
    Act Density 0.026%

    No Known Activations