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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software commands and instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases or sentences that describe actions or processes involving the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Establishment
    -0.64
    sylvania
    -0.61
    ajor
    -0.61
     obliged
    -0.61
    Angelo
    -0.60
    ilight
    -0.60
    obook
    -0.60
    communications
    -0.59
    ights
    -0.58
    central
    -0.58
    POSITIVE LOGITS
     regard
    1.38
    stood
    1.35
     regards
    1.34
    draw
    1.22
    standing
    1.19
     impunity
    1.18
     respect
    1.10
    drawn
    1.00
    holding
    0.97
     dignity
    0.88
    Act Density 0.217%

    No Known Activations