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

    Neuronpedia

    INDEX
    Explanations

    phrases related to "Truck" or "True"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Tru" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     retri
    -0.74
     saline
    -0.65
     indicative
    -0.63
     Lans
    -0.62
     toget
    -0.60
     mysteries
    -0.60
    姫
    -0.59
     Imran
    -0.58
    ãĤº
    -0.58
     theoret
    -0.58
    POSITIVE LOGITS
    cks
    1.04
    kefeller
    0.95
    pling
    0.85
    bone
    0.85
    ourney
    0.84
    pled
    0.81
    ples
    0.80
    itionally
    0.80
    ndra
    0.79
    von
    0.79
    Act Density 0.052%

    No Known Activations